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

    Neuronpedia

    INDEX
    Explanations

    non-consensual acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voli
    0.41
    тина
    0.40
     Pozn
    0.39
    tensorflow
    0.39
    ਿਤ
    0.39
    jelen
    0.38
    TabText
    0.38
    曈
    0.38
    ਿਕ
    0.37
    鿷
    0.36
    POSITIVE LOGITS
    ents
    0.77
    ently
    0.73
    ENTS
    0.72
    encer
    0.71
    encia
    0.71
    enc
    0.70
    ences
    0.69
    ention
    0.66
    ence
    0.64
    enced
    0.64
    Act Density 0.033%

    No Known Activations