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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filler
    -0.07
    武器
    -0.07
     airing
    -0.07
    inen
    -0.07
     الم
    -0.07
    ý
    -0.06
    alem
    -0.06
    \r
    -0.06
    Holder
    -0.06
     brethren
    -0.06
    POSITIVE LOGITS
    InvalidArgumentException
    0.08
    ┹
    0.07
     직
    0.07
     판단
    0.07
     utc
    0.07
    ativas
    0.07
     criticizing
    0.06
    🕝
    0.06
    /version
    0.06
    /unit
    0.06
    Act Density 0.006%

    No Known Activations