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

    Neuronpedia

    INDEX
    Explanations

    tasks for smaller gigs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flamboyant
    0.47
     zweiten
    0.46
     öffentliche
    0.46
     villain
    0.45
     Liebe
    0.44
     Fälle
    0.43
     morality
    0.42
     inadequacy
    0.42
     langfrist
    0.41
     freshmen
    0.41
    POSITIVE LOGITS
    codewords
    0.51
    ভ
    0.51
     ਨੇ
    0.47
     हैन
    0.45
    ERS
    0.45
     ਸਮ
    0.45
     emphasises
    0.45
     தாண்ட
    0.45
     اص
    0.44
     چکے
    0.44
    Act Density 0.002%

    No Known Activations