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

    Neuronpedia

    INDEX
    Explanations

    PROT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awhile
    -0.08
     Providence
    -0.07
    墅
    -0.07
     cx
    -0.07
    ╬
    -0.07
     Số
    -0.07
     concerted
    -0.07
    과장
    -0.07
    健
    -0.07
    財
    -0.07
    POSITIVE LOGITS
     achievable
    0.08
     abrir
    0.08
     Roman
    0.08
     FlatButton
    0.07
     (*
    0.07
    _buy
    0.07
    接收
    0.07
    �
    0.07
     eliminar
    0.07
    _genre
    0.07
    Act Density 0.005%

    No Known Activations