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

    Neuronpedia

    INDEX
    Explanations

    self control/exerting influence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rob
    -0.07
     Attached
    -0.07
    slow
    -0.07
    Quick
    -0.07
    -step
    -0.07
    谈到
    -0.07
    .World
    -0.07
    _Selection
    -0.07
    恋情
    -0.07
     Reich
    -0.07
    POSITIVE LOGITS
    孤儿
    0.07
     доволь
    0.07
    Ѐ
    0.07
     harass
    0.06
    鲦
    0.06
    เศ
    0.06
    _verify
    0.06
    .det
    0.06
    叽
    0.06
    唾
    0.06
    Act Density 0.050%

    No Known Activations