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

    Neuronpedia

    INDEX
    Explanations

    Creation process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (remote
    -0.07
    “How
    -0.06
     Append
    -0.06
     Automated
    -0.06
     fractions
    -0.06
     touchdowns
    -0.06
    .Log
    -0.06
     قیمت
    -0.06
     bases
    -0.06
    _RADIO
    -0.06
    POSITIVE LOGITS
    ehler
    0.08
    üny
    0.07
    aine
    0.07
    ��
    0.07
    loss
    0.06
     Maul
    0.06
    _LSB
    0.06
    iple
    0.06
    ude
    0.06
     danske
    0.06
    Act Density 0.037%

    No Known Activations