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

    Neuronpedia

    INDEX
    Explanations

    descriptive evaluations and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.36
    isme
    0.36
    Итак
    0.29
    ck
    0.29
    frage
    0.28
     droite
    0.28
    ico
    0.27
    ஸ்
    0.27
    ismo
    0.27
    imen
    0.26
    POSITIVE LOGITS
    另一
    0.28
    ᅳ
    0.28
     thisStudent
    0.28
     psycopg
    0.28
     někol
    0.28
    ర్వాత
    0.27
     якщо
    0.27
     keď
    0.27
    というと
    0.27
     disrupt
    0.26
    Act Density 0.134%

    No Known Activations