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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    قب
    -0.07
     Script
    -0.07
    gni
    -0.07
    -base
    -0.07
    ."+
    -0.07
    强制
    -0.07
    (Http
    -0.07
    也没有
    -0.06
    卜
    -0.06
    ambah
    -0.06
    POSITIVE LOGITS
     robin
    0.07
     caval
    0.07
     Ve
    0.07
    touches
    0.07
    _BOUND
    0.07
     Mét
    0.07
    更多的
    0.06
    .putExtra
    0.06
     MATERIAL
    0.06
    阵营
    0.06
    Act Density 0.030%

    No Known Activations