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

    Neuronpedia

    INDEX
    Explanations

    official government information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ार्किक
    0.55
    あ
    0.52
    𝘶
    0.52
     öffent
    0.51
     Djibouti
    0.50
    狧
    0.50
    యర్
    0.50
    𝗮
    0.50
     màu
    0.49
     aberta
    0.49
    POSITIVE LOGITS
    -
    0.60
     differences
    0.56
    ),
    0.55
    '
    0.53
     =
    0.52
    ged
    0.52
     epitome
    0.52
     כמו
    0.50
    melding
    0.50
    noh
    0.50
    Act Density 0.000%

    No Known Activations