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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .activities
    -0.08
    /Error
    -0.08
     ошиб
    -0.08
     עוס
    -0.08
    _CONF
    -0.07
     agré
    -0.07
     perí
    -0.07
    Ȓ
    -0.07
    真皮
    -0.07
    イベ
    -0.07
    POSITIVE LOGITS
    MULT
    0.07
    eneration
    0.07
     Range
    0.07
    hack
    0.06
    olutions
    0.06
    quant
    0.06
    女性朋友
    0.06
    card
    0.06
     Card
    0.06
    PM
    0.06
    Act Density 0.044%

    No Known Activations