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
     дія
    -0.07
    era
    -0.07
    757
    -0.06
    _sin
    -0.06
     Acad
    -0.06
    Alias
    -0.06
    υνα
    -0.06
    [a
    -0.06
    180
    -0.06
    isí
    -0.06
    POSITIVE LOGITS
     the
    0.08
    >');↵↵
    0.08
    /sdk
    0.07
    shint
    0.07
    �은
    0.07
    "The
    0.07
    خ
    0.07
     सच
    0.07
    ท
    0.07
    -the
    0.07
    Act Density 0.375%

    No Known Activations