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

    Neuronpedia

    INDEX
    Explanations

    event listings or announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.80
    OL
    1.35
    '
    1.34
     এ
    1.31
    이스
    1.31
    US
    1.30
     이
    1.27
     إ
    1.26
     구
    1.26
     battlefield
    1.24
    POSITIVE LOGITS
    it
    2.05
    ir
    1.70
     Agustus
    1.61
    ut
    1.48
    ى
    1.47
    ercicio
    1.45
    ik
    1.41
     enero
    1.40
    mäßig
    1.40
     cocinar
    1.39
    Act Density 0.007%

    No Known Activations