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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.90
    and
    0.86
    ↵↵
    0.82
    ...
    0.82
    !
    0.82
    .
    0.80
     and
    0.78
    -
    0.78
    [,
    0.78
    ↵
    0.77
    POSITIVE LOGITS
     ideological
    0.78
     những
    0.77
     aristocratic
    0.77
     heightened
    0.76
     Những
    0.75
    𒄀
    0.74
     disillusion
    0.72
    𒁉
    0.72
     ontological
    0.71
    <unused46>
    0.71
    Act Density 1.219%

    No Known Activations