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

    Neuronpedia

    INDEX
    Explanations

    bew

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ced
    -0.06
     Removes
    -0.06
     Coordinate
    -0.06
    סטוד
    -0.06
     appealed
    -0.06
     Early
    -0.06
    /gl
    -0.06
     teşek
    -0.06
    ted
    -0.06
    自
    -0.06
    POSITIVE LOGITS
     cata
    0.07
    楫
    0.07
    agic
    0.07
    PLIER
    0.07
     التنفيذي
    0.07
    НИ
    0.07
     sands
    0.07
    _PARAMS
    0.07
    $post
    0.07
    <<"\
    0.07
    Act Density 0.070%

    No Known Activations