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

    Neuronpedia

    INDEX
    Explanations

    states women promise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Beacon
    0.50
    ாலத்தில்
    0.49
    Authentication
    0.48
     Америки
    0.48
    TITLE
    0.48
    Preparing
    0.48
     \
    0.47
     America
    0.47
    Cameras
    0.47
    When
    0.47
    POSITIVE LOGITS
     femen
    0.49
    iri
    0.49
     trouser
    0.47
     ergonomic
    0.47
    ेप
    0.45
     hir
    0.45
     reactivation
    0.45
     cadre
    0.45
    χρι
    0.45
     conflicted
    0.44
    Act Density 0.001%

    No Known Activations