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

    Neuronpedia

    INDEX
    Explanations

    gait abnormalities, regression testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    այի
    0.80
    ის
    0.77
    άν
    0.68
    ions
    0.66
    вні
    0.65
     SIINFEKL
    0.64
     SLS
    0.63
    al
    0.63
    די
    0.63
    ᱑
    0.61
    POSITIVE LOGITS
     for
    0.66
    не
    0.63
     ре
    0.62
     com
    0.58
     он
    0.57
    oi
    0.56
     ك
    0.55
    och
    0.55
     о
    0.54
    ي
    0.54
    Act Density 0.012%

    No Known Activations