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

    Neuronpedia

    INDEX
    Explanations

    bs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diam
    -0.07
    ERM
    -0.07
     Sundays
    -0.06
     sunk
    -0.06
    ází
    -0.06
     immedi
    -0.06
    .As
    -0.06
    Sunday
    -0.06
    andas
    -0.06
    92
    -0.06
    POSITIVE LOGITS
     приг
    0.08
     티
    0.07
    anova
    0.07
     предназнач
    0.06
     สล
    0.06
     "\↵
    0.06
     луч
    0.06
    Unix
    0.06
     आई
    0.06
    (Collection
    0.06
    Act Density 0.000%

    No Known Activations