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

    Neuronpedia

    INDEX
    Explanations

    stddef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ȱ
    -0.07
     you
    -0.07
     bleach
    -0.07
    잔
    -0.07
     Problem
    -0.07
     lucky
    -0.06
    влажн
    -0.06
     storm
    -0.06
     Reminder
    -0.06
    อาคาร
    -0.06
    POSITIVE LOGITS
     ليبيا
    0.07
    wstring
    0.07
     Fred
    0.07
    _student
    0.07
     ew
    0.07
    ESPN
    0.07
    _W
    0.07
     נה
    0.07
    'D
    0.07
     Tf
    0.07
    Act Density 0.016%

    No Known Activations