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

    Neuronpedia

    INDEX
    Explanations

    side effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     واب
    -0.07
    ynı
    -0.06
    estructor
    -0.06
    찰
    -0.06
     klid
    -0.06
    音
    -0.06
     testament
    -0.06
    chandle
    -0.06
     amsterdam
    -0.06
    [e
    -0.06
    POSITIVE LOGITS
    157
    0.07
     obl
    0.07
     perme
    0.07
     sanitize
    0.06
    eslint
    0.06
     Jessie
    0.06
    allo
    0.06
    �
    0.06
     socks
    0.06
     MainForm
    0.06
    Act Density 0.022%

    No Known Activations