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

    Neuronpedia

    INDEX
    Explanations

    'an' or 'the' followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.63
     headway
    0.59
    الم
    0.54
     planks
    0.53
     warts
    0.52
    し
    0.52
    L
    0.51
    T
    0.50
     warms
    0.49
    place
    0.49
    POSITIVE LOGITS
     번째
    0.51
    ка
    0.48
    르
    0.48
    ro
    0.46
    티
    0.46
    יה
    0.44
    Inicio
    0.44
     Какой
    0.44
     fece
    0.43
     Και
    0.43
    Act Density 0.002%

    No Known Activations