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

    Neuronpedia

    INDEX
    Explanations

    guarantee, Nike, safety, bioadhesive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.95
    u
    0.95
    uws
    0.79
    ו
    0.79
    торов
    0.77
    uaries
    0.74
     существенно
    0.74
    ვ
    0.74
    得很
    0.73
    e
    0.73
    POSITIVE LOGITS
    NESS
    0.84
    MI
    0.82
    AN
    0.82
    ILL
    0.81
    AI
    0.80
    MEDIA
    0.80
    nip
    0.79
    PES
    0.79
    MAN
    0.76
    PF
    0.76
    Act Density 0.001%

    No Known Activations