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

    Neuronpedia

    INDEX
    Explanations

    business IT and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$;
    0.65
    𝖐
    0.63
     Änderung
    0.62
    ’।
    0.61
     gleiche
    0.61
     Teilen
    0.61
     použí
    0.60
     باستخدام
    0.59
    followfollow
    0.59
     různ
    0.57
    POSITIVE LOGITS
     can
    0.72
     are
    0.65
     in
    0.64
     will
    0.63
     would
    0.61
    C
    0.60
     was
    0.60
    T
    0.60
     t
    0.59
     is
    0.58
    Act Density 0.034%

    No Known Activations