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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCO
    -0.07
    aybe
    -0.07
    中介机构
    -0.06
     cont
    -0.06
    🔜
    -0.06
    ��
    -0.06
     RuntimeMethod
    -0.06
    .bunifu
    -0.06
    _LESS
    -0.06
     secondo
    -0.06
    POSITIVE LOGITS
     warmth
    0.08
     gehen
    0.07
    ALAR
    0.07
     RL
    0.07
    olar
    0.07
     visits
    0.07
    acaktır
    0.07
     aggression
    0.07
     הגבוה
    0.07
     antagon
    0.07
    Act Density 0.020%

    No Known Activations