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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    This neuron is detecting floating-point numeric literals in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	Y
    -0.07
     suburbs
    -0.07
    _Font
    -0.07
    ->{$
    -0.06
     malware
    -0.06
    ربه
    -0.06
    _
↵
    -0.06
    Unexpected
    -0.06
     TV
    -0.06
    ;\↵
    -0.06
    POSITIVE LOGITS
     كس
    0.07
    latable
    0.07
    ensions
    0.07
     Každ
    0.06
     poslední
    0.06
    nelle
    0.06
    telefone
    0.06
     Sabb
    0.06
     สำ
    0.06
    striction
    0.06
    Act Density 0.237%

    No Known Activations