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

    Neuronpedia

    INDEX
    Explanations

    tokenization and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ospitals
    0.81
    сные
    0.78
    idenav
    0.75
    hoea
    0.74
    withTrashed
    0.74
    𝗽
    0.72
    publications
    0.71
    classifier
    0.71
    اب
    0.70
     líquidos
    0.70
    POSITIVE LOGITS
    可以
    0.75
    我可以
    0.73
     longtime
    0.70
    नेत
    0.69
     undeniably
    0.69
     arithmetic
    0.68
     Emmy
    0.67
    可以是
    0.67
     guarant
    0.66
     compatible
    0.65
    Act Density 0.001%

    No Known Activations