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

    Neuronpedia

    INDEX
    Explanations

    stop, avoid, emulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.85
    ht
    0.77
    tidy
    0.74
    owi
    0.74
    辦法
    0.73
     Pond
    0.71
    ว่าง
    0.71
    wati
    0.71
    tid
    0.68
    ll
    0.67
    POSITIVE LOGITS
    idescent
    0.84
     були
    0.80
    м
    0.80
    ਨ
    0.77
    是通过
    0.77
     monoch
    0.77
    Linea
    0.77
    Syst
    0.77
    은
    0.75
     फीसद
    0.74
    Act Density 0.001%

    No Known Activations