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

    Neuronpedia

    INDEX
    Explanations

    divers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cock
    -0.07
    أسباب
    -0.07
    adem
    -0.07
    Bed
    -0.07
    .setParent
    -0.07
     thành
    -0.07
    评估
    -0.06
    Defined
    -0.06
     بم
    -0.06
    -_
    -0.06
    POSITIVE LOGITS
     divers
    0.08
     apolog
    0.07
    qrstuvwxyz
    0.07
    โดน
    0.07
     loops
    0.07
     CONSEQUENTIAL
    0.07
    )dealloc
    0.07
    iero
    0.07
    DEFAULT
    0.07
    峿
    0.07
    Act Density 0.004%

    No Known Activations