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

    Neuronpedia

    INDEX
    Explanations

    decode bytes to string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ого
    0.96
     Glove
    0.79
     Downloads
    0.78
    ܘ
    0.78
     diamond
    0.77
     Autobi
    0.76
    وہ
    0.75
     useParams
    0.73
     Diamond
    0.73
    DeleteDialogOpen
    0.73
    POSITIVE LOGITS
    ("
    0.75
    ('
    0.73
    ?).
    0.72
     ("
    0.71
    (".
    0.70
     \%)$.
    0.69
    ()).
    0.69
    ).}
    0.69
     ('
    0.67
     \%$.
    0.65
    Act Density 0.004%

    No Known Activations