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

    Neuronpedia

    INDEX
    Explanations

    introduces clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    le
    -2.08
    </td>
    -1.99
     This
    -1.88
    in
    -1.87
     allzu
    -1.77
    、
    -1.75
     hechas
    -1.70
    /…
    -1.67
    and
    -1.66
    蛳
    -1.66
    POSITIVE LOGITS
     a
    2.05
    ଢ
    1.86
    __":
    1.71
    zeman
    1.69
     concepción
    1.67
    ſelves
    1.66
     \%}$
    1.65
    uç
    1.64
    existsSync
    1.64
    𖤍
    1.60
    Act Density 0.015%

    No Known Activations