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

    Neuronpedia

    INDEX
    Explanations

    path and file operations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     STAFF
    0.61
    Omn
    0.60
    هم
    0.59
    Always
    0.59
     CUSTOM
    0.58
     ہمیشہ
    0.57
     petugas
    0.57
     MEDIA
    0.57
    PARENT
    0.57
    Innov
    0.56
    POSITIVE LOGITS
     kil
    0.64
    िप्स
    0.63
     tidy
    0.61
     kasi
    0.61
    kil
    0.59
    ajo
    0.59
    ravariant
    0.58
     flung
    0.57
     אז
    0.57
     कमि
    0.56
    Act Density 0.000%

    No Known Activations