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

    Neuronpedia

    INDEX
    Explanations

    account mentions and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    https
    0.53
    -,
    0.52
    :}
    0.50
    :\\
    0.49
    http
    0.49
    íns
    0.48
    agreement
    0.48
    _:
    0.47
     Untersuchungen
    0.47
    enium
    0.46
    POSITIVE LOGITS
     (@
    0.62
     advocate
    0.43
    0.43
     dazz
    0.41
     fans
    0.41
     fanatics
    0.41
     truckers
    0.41
     videojuegos
    0.40
     (’
    0.39
     vidéo
    0.39
    Act Density 0.001%

    No Known Activations