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

    Neuronpedia

    INDEX
    Explanations

    Negative consequences or risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uesday
    -0.07
    力
    -0.07
    ��
    -0.07
    sys
    -0.07
    청소
    -0.07
    Chef
    -0.07
    湛
    -0.06
    内
    -0.06
     الدفاع
    -0.06
    gráf
    -0.06
    POSITIVE LOGITS
    放到
    0.08
    .isArray
    0.07
    instant
    0.07
    Floating
    0.06
    投入到
    0.06
    gtest
    0.06
     lunar
    0.06
    跑到
    0.06
    IPH
    0.06
    urniture
    0.06
    Act Density 0.126%

    No Known Activations