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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Picks
    -0.08
     applaud
    -0.08
    Jur
    -0.07
    Dismiss
    -0.07
    Les
    -0.07
    곡
    -0.07
    ＋
    -0.07
     ↓
    -0.07
    ttp
    -0.07
    exo
    -0.07
    POSITIVE LOGITS
    帱
    0.07
    Eventually
    0.07
     untuk
    0.07
    periment
    0.07
    ㅆ
    0.07
    Ⲧ
    0.07
     swiftly
    0.07
    _ru
    0.06
    -shared
    0.06
    🐓
    0.06
    Act Density 0.017%

    No Known Activations