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

    Neuronpedia

    INDEX
    Explanations

    Nevertheless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DialogInterface
    -0.07
    ↵    ↵↵
    -0.06
    estar
    -0.06
     recruiter
    -0.06
    .getColumnIndex
    -0.06
    itched
    -0.06
    Saudi
    -0.06
    AMESPACE
    -0.06
    ileceğini
    -0.06
     Только
    -0.06
    POSITIVE LOGITS
     devour
    0.07
    /es
    0.07
    科技
    0.07
     vyu
    0.07
     Franco
    0.07
     excessive
    0.07
    _diag
    0.07
     себ
    0.07
    _bonus
    0.07
    .fd
    0.07
    Act Density 0.008%

    No Known Activations