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

    Neuronpedia

    INDEX
    Explanations

    ingredients in recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     były
    0.39
     był
    0.37
    ewnątrz
    0.34
     trưởng
    0.34
     Cicero
    0.34
    함으로써
    0.34
     OrderedDict
    0.34
     وړاند
    0.34
     śmier
    0.34
    财政
    0.33
    POSITIVE LOGITS
    plus
    0.40
    [
    0.39
     डालकर
    0.38
     liqueur
    0.38
     మీకు
    0.38
    cheduled
    0.37
    टीसी
    0.36
     notification
    0.36
     fermentation
    0.36
    泂
    0.35
    Act Density 0.068%

    No Known Activations