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

    Neuronpedia

    INDEX
    Explanations

    copyright

    np_max-act · gemini-2.0-flash

    The neuron detects copyright and legal‐permission notices in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    akte
    -0.07
     worked
    -0.07
    ंभ
    -0.06
    igrams
    -0.06
    Parameter
    -0.06
    UE
    -0.06
    amma
    -0.06
    .values
    -0.06
    .Client
    -0.06
     were
    -0.06
    POSITIVE LOGITS
     ['$
    0.08
    ん
    0.07
     Datagram
    0.07
     audition
    0.07
    θεν
    0.07
     haul
    0.07
     unilateral
    0.07
     TString
    0.06
     نقاط
    0.06
     الجن
    0.06
    Act Density 0.007%

    No Known Activations