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

    Neuronpedia

    INDEX
    Explanations

    others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     silicon
    -0.07
    信用
    -0.07
     gamb
    -0.07
    Every
    -0.06
    Insurance
    -0.06
     consec
    -0.06
    issan
    -0.06
    [val
    -0.06
     Silicon
    -0.06
    赵
    -0.06
    POSITIVE LOGITS
     others
    0.17
     Others
    0.14
    Others
    0.10
    ers
    0.09
    ter
    0.08
    ERS
    0.08
    atri
    0.08
    vers
    0.07
     Scatter
    0.07
     Differences
    0.07
    Act Density 0.021%

    No Known Activations