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

    Neuronpedia

    INDEX
    Explanations

    up/out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вь
    0.72
    ቶ
    0.71
    ie
    0.71
    ਦਰ
    0.71
    瑭
    0.70
     교육
    0.70
     effector
    0.69
     तमाम
    0.69
    نين
    0.68
     undang
    0.67
    POSITIVE LOGITS
     collapsible
    0.84
     Bumble
    0.73
     Möbius
    0.73
     prü
    0.72
     BLAST
    0.71
     coke
    0.71
    ypse
    0.70
     combustible
    0.69
    bene
    0.69
    tain
    0.69
    Act Density 0.001%

    No Known Activations