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

    Neuronpedia

    INDEX
    Explanations

    anger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _input
    -0.08
     저장
    -0.07
    .payload
    -0.07
     agreg
    -0.07
    /qu
    -0.07
     yếu
    -0.07
    expired
    -0.06
    .Full
    -0.06
    atab
    -0.06
     appointments
    -0.06
    POSITIVE LOGITS
    交给
    0.07
     Рас
    0.07
    ай
    0.07
    erto
    0.07
    ี้
    0.07
     Tür
    0.07
    \"><
    0.07
    ꒪
    0.07
    ירו
    0.07
    휴
    0.07
    Act Density 0.053%

    No Known Activations