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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    💗
    -0.08
     urn
    -0.08
    (edges
    -0.07
    SeekBar
    -0.07
    쎄
    -0.07
    不是一个
    -0.07
     invitations
    -0.07
    变得
    -0.07
    !!
    -0.07
    /swagger
    -0.07
    POSITIVE LOGITS
     dialect
    0.08
    ynthesis
    0.07
    货币
    0.07
    TP
    0.07
    扩散
    0.07
     против
    0.07
    Manufact
    0.07
     hoạt
    0.07
     printing
    0.07
     decoding
    0.07
    Act Density 0.003%

    No Known Activations