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

    Neuronpedia

    INDEX
    Explanations

    DOIs and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sexism
    0.44
     sexist
    0.44
     misog
    0.42
     chival
    0.42
     ecologists
    0.40
     Saj
    0.38
     rescaling
    0.38
     scaling
    0.38
    ))(
    0.38
     nem
    0.38
    POSITIVE LOGITS
    ත්
    0.45
    يش
    0.44
     фонд
    0.42
     било
    0.38
    σουμε
    0.38
    inträ
    0.37
    arın
    0.37
    لے
    0.36
    浔
    0.36
    ilikom
    0.35
    Act Density 0.001%

    No Known Activations