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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     질문
    -0.07
    ета
    -0.07
    CLUSIVE
    -0.07
    ATEGORIES
    -0.06
     nói
    -0.06
    уре
    -0.06
    .Controls
    -0.06
     Ты
    -0.06
     повідом
    -0.06
    _phone
    -0.06
    POSITIVE LOGITS
    -signed
    0.07
    (express
    0.07
    How
    0.06
    healthy
    0.06
    ']="
    0.06
    摘
    0.06
    ,ev
    0.06
    ')){↵
    0.06
    (ec
    0.06
     Fucked
    0.06
    Act Density 0.018%

    No Known Activations