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
     المؤ
    -0.07
    ({...
    -0.07
    -C
    -0.06
     incor
    -0.06
    ไฟล
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    (auto
    -0.06
     takdir
    -0.06
    $L
    -0.06
     soc
    -0.06
    POSITIVE LOGITS
     the
    0.07
     metam
    0.06
     vess
    0.06
     Appearance
    0.06
    стоя
    0.06
     beim
    0.06
     pedestrians
    0.06
    ансов
    0.06
    pname
    0.06
    hower
    0.06
    Act Density 0.060%

    No Known Activations