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

    Neuronpedia

    INDEX
    Explanations

    Google Drive files and application launching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ung
    0.47
    inv
    0.46
    ut
    0.45
    hal
    0.44
    emb
    0.43
    ot
    0.43
    em
    0.42
    station
    0.41
    á
    0.41
     dos
    0.40
    POSITIVE LOGITS
     ivvu
    0.44
    ديث
    0.43
    льнявыя
    0.42
    يمان
    0.42
    وازن
    0.41
     marquées
    0.41
     अहमदाबाद
    0.40
    Cory
    0.39
    0.39
     Elytres
    0.39
    Act Density 0.000%

    No Known Activations