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

    Neuronpedia

    INDEX
    Explanations

    `do`, `sudo`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मधील
    1.13
    ल
    1.07
     inglês
    1.05
     ouverte
    1.03
     alemão
    1.02
     atractivo
    0.99
     equates
    0.98
     boosts
    0.94
     awakens
    0.93
     anglès
    0.92
    POSITIVE LOGITS
    ad
    1.09
    s
    1.03
    se
    0.94
     se
    0.93
     потер
    0.93
    minent
    0.91
     Petition
    0.88
    c
    0.87
    ූප
    0.86
    瞽
    0.86
    Act Density 0.019%

    No Known Activations