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

    Neuronpedia

    INDEX
    Explanations

    media and descriptions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ちゃんと
    0.64
    펌
    0.64
    restart
    0.62
    érons
    0.62
    ძლ
    0.61
    اہم
    0.60
    മൂഹ
    0.59
    щено
    0.58
    र्तन
    0.57
     液
    0.57
    POSITIVE LOGITS
     purportedly
    0.67
     hedon
    0.64
     conclu
    0.61
     seaf
    0.61
     Kalah
    0.61
     inkl
    0.60
    gah
    0.60
     Ninth
    0.59
    yh
    0.59
     exclus
    0.59
    Act Density 0.000%

    No Known Activations