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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โฆ
    -0.07
    _utilities
    -0.07
     ninja
    -0.07
    odef
    -0.07
     textbook
    -0.07
    Andy
    -0.07
    .foundation
    -0.06
    _COUNTER
    -0.06
     audition
    -0.06
     APA
    -0.06
    POSITIVE LOGITS
     minded
    0.07
     sayısı
    0.06
    وير
    0.06
    атегор
    0.06
     days
    0.06
     getApp
    0.06
    tems
    0.06
     нашем
    0.06
     valores
    0.06
    MS
    0.06
    Act Density 0.023%

    No Known Activations