Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    detailed procedural steps related to chemical production processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily fires on numeric tokens representing decimal values (i.e. numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /signup
    -0.07
     учеб
    -0.07
     surgeon
    -0.07
    .setup
    -0.07
     sever
    -0.06
     insurer
    -0.06
     Revolutionary
    -0.06
    IMA
    -0.06
     захід
    -0.06
     fracture
    -0.06
    POSITIVE LOGITS
     모두
    0.06
     προϊ
    0.06
    	TokenName
    0.06
    (CancellationToken
    0.06
    (HttpContext
    0.06
    ح
    0.06
    _And
    0.06
     ।↵↵
    0.06
    _nome
    0.06
     DISCLAIMED
    0.06
    Act Density 0.008%

    No Known Activations