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

    Neuronpedia

    INDEX
    Explanations

    Code/Computer snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilim
    -0.07
    .steps
    -0.06
     rooft
    -0.06
    sat
    -0.06
     vanity
    -0.06
    LR
    -0.06
     delt
    -0.06
    回答
    -0.06
    .comments
    -0.06
    FO
    -0.06
    POSITIVE LOGITS
     Authentication
    0.07
    Anime
    0.07
     tableView
    0.07
     न
    0.07
     mur
    0.07
    winter
    0.06
     Albert
    0.06
     Countdown
    0.06
    OnInit
    0.06
     neu
    0.06
    Act Density 0.000%

    No Known Activations