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

    Neuronpedia

    INDEX
    Explanations

    am prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     articles
    0.66
     Everything
    0.66
     건
    0.65
     Articles
    0.64
    стки
    0.63
     locally
    0.63
     Messer
    0.63
     laundry
    0.63
     Optional
    0.62
     Compare
    0.62
    POSITIVE LOGITS
    ethyst
    1.17
    iguous
    1.10
    sterdam
    1.07
    iguity
    1.06
    orphous
    1.05
    adeus
    0.97
    assadors
    0.96
    oung
    0.96
    ંત્રણ
    0.94
    icus
    0.92
    Act Density 0.052%

    No Known Activations