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

    Neuronpedia

    INDEX
    Explanations

    Inscriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on bits of text enclosed in quotation marks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AlmostEqual
    -0.07
     nové
    -0.07
    adam
    -0.07
     tasks
    -0.06
    ्श
    -0.06
    /reg
    -0.06
    (png
    -0.06
     diseñador
    -0.06
    (x
    -0.06
     nových
    -0.06
    POSITIVE LOGITS
    _supply
    0.07
     Weekly
    0.06
     Belt
    0.06
     Points
    0.06
     smallest
    0.06
    _pal
    0.06
    	index
    0.06
     Detailed
    0.06
    (cluster
    0.06
    cep
    0.06
    Act Density 0.058%

    No Known Activations