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

    Neuronpedia

    INDEX
    Explanations

    past tense feminine verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شدن
    0.77
    pte
    0.70
    idać
    0.68
    ភេទ
    0.68
     entsteht
    0.67
    τούν
    0.66
    Yours
    0.66
    éndose
    0.65
     straightened
    0.64
     manufactured
    0.64
    POSITIVE LOGITS
     bila
    1.15
    ровала
    1.06
     dala
    1.04
    нила
    1.02
     rekla
    0.97
    чала
    0.96
    rala
    0.96
     била
    0.91
    вала
    0.91
     Bila
    0.91
    Act Density 0.047%

    No Known Activations