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

    Neuronpedia

    INDEX
    Explanations

    private words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ush
    0.39
    lust
    0.38
    :‏
    0.38
    attributes
    0.37
    졀
    0.37
    ros
    0.36
     crisp
    0.36
    prung
    0.36
    ஓம்
    0.36
    dyn
    0.36
    POSITIVE LOGITS
     privati
    0.46
     понима
    0.38
     funzione
    0.37
     privately
    0.37
     privato
    0.36
     privée
    0.36
     निजी
    0.36
     hated
    0.36
    剰
    0.36
     minor
    0.35
    Act Density 0.000%

    No Known Activations