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

    Neuronpedia

    INDEX
    Explanations

    website addresses with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    走下去
    -0.07
     איפה
    -0.06
     Soil
    -0.06
     ...↵↵
    -0.06
    xaa
    -0.06
    　
    -0.06
    uali
    -0.06
    复合
    -0.06
    ul
    -0.06
     believe
    -0.06
    POSITIVE LOGITS
    _norm
    0.07
    层层
    0.07
    pretty
    0.07
    _RESP
    0.06
     inversion
    0.06
    itten
    0.06
    秦皇岛
    0.06
     kost
    0.06
     Sen
    0.06
     posY
    0.06
    Act Density 0.001%

    No Known Activations