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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руется
    -0.07
    /*
↵
    -0.06
    |`↵
    -0.06
    KeyEvent
    -0.06
     lim
    -0.06
     Gender
    -0.06
    -/
    -0.06
     �
    -0.06
     ()↵
    -0.06
    setSize
    -0.06
    POSITIVE LOGITS
    Enumer
    0.07
     мощ
    0.06
    记录
    0.06
    攻
    0.06
     pulp
    0.06
    .Azure
    0.06
    .LogError
    0.06
     клуб
    0.06
    .met
    0.06
     Arts
    0.06
    Act Density 0.002%

    No Known Activations