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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piè
    0.45
     pie
    0.43
     circost
    0.43
     circunst
    0.43
     ż
    0.42
     ti
    0.42
     iza
    0.41
     crist
    0.40
     peny
    0.39
     trae
    0.39
    POSITIVE LOGITS
    ender
    0.41
    чко
    0.40
    сле
    0.40
     моди
    0.38
    Ку
    0.38
     காப்பா
    0.37
     Converse
    0.37
     Lifecycle
    0.36
    </h2>
    0.36
     процес
    0.35
    Act Density 0.006%

    No Known Activations