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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SW
    -0.07
     první
    -0.07
    _phrase
    -0.06
     Sovere
    -0.06
    �
    -0.06
     Expires
    -0.06
     친
    -0.06
    otherwise
    -0.06
     gimm
    -0.06
     Benefit
    -0.06
    POSITIVE LOGITS
     bons
    0.06
    _Thread
    0.06
     tess
    0.06
    LECT
    0.06
     conexao
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
    .Physics
    0.06
     は
    0.06
    ชร
    0.06
    망
    0.06
    Act Density 0.032%

    No Known Activations