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

    Neuronpedia

    INDEX
    Explanations

    Lewis Carroll, Lewis Hamilton, Lewis Wilson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuttings
    1.85
     Pelosi
    1.84
    تور
    1.84
     Caesars
    1.77
     Doremi
    1.73
     Jimin
    1.73
     Akufo
    1.72
    憾
    1.71
     advis
    1.66
    iftoire
    1.66
    POSITIVE LOGITS
    ι
    2.31
    ona
    2.19
    ре
    2.17
    ina
    2.17
    ä
    2.06
    ist
    2.03
    м
    1.98
    il
    1.96
    är
    1.95
    ati
    1.91
    Act Density 0.000%

    No Known Activations