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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     输入
    -0.07
    _fwd
    -0.06
    ollision
    -0.06
    (Location
    -0.06
    akhstan
    -0.06
    ющие
    -0.06
     Artem
    -0.06
    ticket
    -0.06
     Kazakhstan
    -0.06
    667
    -0.06
    POSITIVE LOGITS
     tờ
    0.08
    サー
    0.07
    腹
    0.07
    ống
    0.07
    、本
    0.06
     ochran
    0.06
    UTOR
    0.06
     preca
    0.06
     �
    0.06
     &(
    0.06
    Act Density 0.005%

    No Known Activations