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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stephan
    -0.07
    stp
    -0.07
    �ng
    -0.06
    getFile
    -0.06
    Doc
    -0.06
     Pr
    -0.06
     IG
    -0.06
     Jo
    -0.06
     خود
    -0.06
    kind
    -0.06
    POSITIVE LOGITS
    "",
    0.06
    quoi
    0.06
    Tumblr
    0.06
    Tonight
    0.06
    arching
    0.06
     resembled
    0.06
     MPEG
    0.05
     zev
    0.05
     bestellen
    0.05
    一卷
    0.05
    Act Density 0.001%

    No Known Activations