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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (board
    -0.07
    _cover
    -0.07
    _Bl
    -0.07
    تمويل
    -0.07
    NET
    -0.07
    运费
    -0.07
    担当
    -0.06
    Identity
    -0.06
    knowledge
    -0.06
    //
    -0.06
    POSITIVE LOGITS
    Delta
    0.07
    容器
    0.07
     deviations
    0.07
    [U
    0.07
    _",
    0.07
     иногда
    0.07
    INLINE
    0.06
     Delta
    0.06
     DIV
    0.06
     Δ
    0.06
    Act Density 0.002%

    No Known Activations