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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ink
    -0.08
    _beh
    -0.07
    uir
    -0.07
    اجه
    -0.06
     interference
    -0.06
     ISIL
    -0.06
     reiterated
    -0.06
    ंधन
    -0.06
    하여
    -0.06
     interf
    -0.06
    POSITIVE LOGITS
    399
    0.06
     vš
    0.06
    díl
    0.06
     {↵
    0.06
    (point
    0.06
     */
↵
    0.06
    "context
    0.06
     smirk
    0.06
    .Actions
    0.06
     LOGIN
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.