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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    methodVisitor
    -0.08
    甗
    -0.07
    蔃
    -0.07
    влаж
    -0.07
    enqueue
    -0.07
     זוכר
    -0.07
    гу
    -0.07
    自然而然
    -0.07
     fireEvent
    -0.07
    黔
    -0.07
    POSITIVE LOGITS
    Voice
    0.07
    _ALERT
    0.07
    IKE
    0.06
    _sim
    0.06
     Counseling
    0.06
    _DETAIL
    0.06
    却没有
    0.06
    District
    0.06
     neg
    0.06
    市场需求
    0.06
    Act Density 0.002%

    No Known Activations