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

    Neuronpedia

    INDEX
    Explanations

    Stephen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stephen
    -0.47
    rungsseite
    -0.45
    yarnpkg
    -0.43
    Stephen
    -0.43
    verwijspagina
    -0.43
     becoming
    -0.42
     ў
    -0.42
     макси
    -0.42
    PDIR
    -0.42
     coming
    -0.41
    POSITIVE LOGITS
    ing
    0.92
    ️
    0.91
     pleaſure
    0.90
     Monfieur
    0.88
     ſtate
    0.84
    izability
    0.82
    ScopeManager
    0.80
     itſelf
    0.79
    ings
    0.79
     ―――――
    0.79
    Act Density 0.166%

    No Known Activations