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

    Neuronpedia

    INDEX
    Explanations

    cascade classifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ብስብ
    1.09
    ት
    1.07
    Czas
    1.01
    Metaxy
    1.00
    许
    1.00
     aesthetically
    0.99
     forego
    0.97
    в
    0.97
     SPDX
    0.96
     voyez
    0.95
    POSITIVE LOGITS
    ين
    1.36
    are
    1.25
    да
    1.20
    c
    1.11
    a
    1.05
    inches
    1.02
    union
    1.01
    iv
    1.00
    ).)
    0.94
    logging
    0.93
    Act Density 0.005%

    No Known Activations