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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revolves
    -0.07
    €“
    -0.06
    (local
    -0.06
     ensures
    -0.06
    情報
    -0.06
    _WH
    -0.06
    strukce
    -0.06
    noDB
    -0.06
     فرو
    -0.06
     Lew
    -0.06
    POSITIVE LOGITS
     случаев
    0.07
    pins
    0.07
     득
    0.07
    png
    0.06
     Güney
    0.06
    없
    0.06
    (gulp
    0.06
    èles
    0.06
     INV
    0.06
     Demir
    0.06
    Act Density 0.424%

    No Known Activations