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

    Neuronpedia

    INDEX
    Explanations

    links and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.69
    ,
    0.61
    )
    0.54
     some
    0.52
     corn
    0.52
     where
    0.52
    }
    0.50
     cor
    0.50
     despite
    0.49
     a
    0.49
    POSITIVE LOGITS
    𒅗
    0.68
    ayvachi
    0.61
    𒃶
    0.61
     रीजनिंग
    0.60
    CCIÓN
    0.60
    <unused1711>
    0.58
    𒌇
    0.58
    Nonnull
    0.58
     Analytics
    0.58
    𒋫
    0.57
    Act Density 0.925%

    No Known Activations