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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    降到
    -0.08
    LD
    -0.07
    Link
    -0.07
     Fleming
    -0.07
     religious
    -0.07
     acceptance
    -0.07
    പ
    -0.07
    â
    -0.06
    解答
    -0.06
    /ph
    -0.06
    POSITIVE LOGITS
    _Select
    0.07
    -group
    0.07
    _global
    0.07
    _SELF
    0.06
    边际
    0.06
    سين
    0.06
    _employee
    0.06
    StandardItem
    0.06
     США
    0.06
    _ATTACK
    0.06
    Act Density 0.004%

    No Known Activations