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

    Neuronpedia

    INDEX
    Explanations

    latex math mode delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让你
    0.33
    坟
    0.29
    引导
    0.29
     කොට
    0.29
    藓
    0.29
    很简单
    0.29
    正确
    0.28
     当然
    0.28
    也就是说
    0.27
    节点
    0.27
    POSITIVE LOGITS
     presence
    0.29
    USB
    0.28
    F
    0.28
    p
    0.28
     \
    0.27
    SP
    0.27
    SM
    0.27
     filmy
    0.27
     \%
    0.27
     }^{\
    0.26
    Act Density 0.054%

    No Known Activations