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

    Neuronpedia

    INDEX
    Explanations

    Legal/Formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !='
    -0.06
    patches
    -0.06
     cold
    -0.06
     peace
    -0.06
     lost
    -0.06
     browsing
    -0.06
    urate
    -0.06
    онь
    -0.06
    人員
    -0.06
    년에
    -0.06
    POSITIVE LOGITS
    Wer
    0.07
     obstacles
    0.07
     erk
    0.07
    _transfer
    0.07
     twins
    0.07
    _edges
    0.06
    Knife
    0.06
     Gef
    0.06
     Gel
    0.06
    ерин
    0.06
    Act Density 0.000%

    No Known Activations