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

    Neuronpedia

    INDEX
    Explanations

    Blame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collage
    -0.07
     kort
    -0.07
     Ferguson
    -0.07
     syst
    -0.07
    ५
    -0.07
     vigorous
    -0.07
     essay
    -0.07
     toughness
    -0.07
     sess
    -0.07
     corporation
    -0.07
    POSITIVE LOGITS
     blame
    0.11
     blaming
    0.10
     blamed
    0.10
     blames
    0.09
    look
    0.07
    _FAULT
    0.07
    İTESİ
    0.06
    looking
    0.06
     Timing
    0.06
    FORM
    0.06
    Act Density 0.004%

    No Known Activations