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

    Neuronpedia

    INDEX
    Explanations

    mit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     from
    -0.07
    .turn
    -0.07
    ajo
    -0.07
     Dense
    -0.06
     ώ
    -0.06
     Darren
    -0.06
     cavern
    -0.06
     robbery
    -0.06
     municipality
    -0.06
     HashSet
    -0.06
    POSITIVE LOGITS
    �
    0.06
     traged
    0.06
    AppName
    0.06
    ecc
    0.06
    ＊
    0.06
    _DISPLAY
    0.06
    _script
    0.06
    shima
    0.06
    SED
    0.06
    mic
    0.06
    Act Density 0.027%

    No Known Activations