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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弥
    -0.07
     hayata
    -0.07
    _token
    -0.06
    `='$
    -0.06
     Ao
    -0.06
    ُّ
    -0.06
    つぶ
    -0.06
    Tue
    -0.06
    無
    -0.06
     Deg
    -0.06
    POSITIVE LOGITS
     Workflow
    0.07
    racuse
    0.06
     tick
    0.06
    .clips
    0.06
     Amerikan
    0.06
    forcer
    0.06
     Сем
    0.06
     كور
    0.06
     graves
    0.06
    PUTE
    0.06
    Act Density 0.000%

    No Known Activations