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

    Neuronpedia

    INDEX
    Explanations

    results, benefits, impact, consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.37
    ning
    0.31
     an
    0.30
    \
    0.30
    I
    0.29
     are
    0.26
    0.26
     bank
    0.26
    ö
    0.26
    lain
    0.25
    POSITIVE LOGITS
    al
    0.39
    at
    0.36
    ad
    0.35
    ла
    0.35
    ன்
    0.33
    ות
    0.33
    ar
    0.32
    in
    0.31
    ட
    0.29
     Aplic
    0.29
    Act Density 0.716%

    No Known Activations