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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quotelev
    -0.08
    ту
    -0.08
    褪
    -0.07
    íveis
    -0.07
    🦋
    -0.07
     люди
    -0.07
    🌷
    -0.07
    靛
    -0.07
     brilliant
    -0.07
    راء
    -0.07
    POSITIVE LOGITS
     STOCK
    0.08
    ﺼ
    0.07
     syslog
    0.07
    _signed
    0.07
    .report
    0.07
     kullanıcı
    0.06
    _CC
    0.06
     statuses
    0.06
     cooldown
    0.06
     rank
    0.06
    Act Density 0.000%

    No Known Activations