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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shouting
    -0.08
    <V
    -0.07
     overwhelmingly
    -0.07
    ≌
    -0.06
    ◊
    -0.06
    emotion
    -0.06
     assertions
    -0.06
    ѫ
    -0.06
    级
    -0.06
    _num
    -0.06
    POSITIVE LOGITS
    browser
    0.07
    不妨
    0.07
    厦门
    0.07
    .......
    0.06
    duto
    0.06
     Limited
    0.06
    идент
    0.06
    دائرة
    0.06
    ارية
    0.06
    っていて
    0.06
    Act Density 0.002%

    No Known Activations