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

    Neuronpedia

    INDEX
    Explanations

    a mix of numbers, names, and medical terms, especially where there are version issues

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    viste
    -0.40
    ParallelGroup
    -0.40
    ISES
    -0.40
    
    -0.40
    чески
    -0.39
    entro
    -0.39
    AspNetCore
    -0.38
     []:
    -0.38
    sibles
    -0.38
    providedIn
    -0.38
    POSITIVE LOGITS
     faſt
    0.84
     pleaſure
    0.84
     auffi
    0.83
     about
    0.82
    neſs
    0.81
     raiſ
    0.81
     our
    0.81
     purpoſe
    0.80
     your
    0.79
     their
    0.79
    Act Density 15.066%

    No Known Activations