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

    Neuronpedia

    INDEX
    Explanations

    outstanding in his field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eleven
    0.48
    Eleven
    0.40
     eleven
    0.39
     मिट्टी
    0.38
     Thirteen
    0.38
     Morrison
    0.38
    十三
    0.37
    lensFlare
    0.37
    颜色
    0.36
     thirteen
    0.36
    POSITIVE LOGITS
    replace
    0.40
    वाह
    0.37
    lib
    0.35
    ingt
    0.35
     Absolutely
    0.34
    astrous
    0.34
    replaceAll
    0.34
    வ
    0.34
    tre
    0.33
    かり
    0.33
    Act Density 0.002%

    No Known Activations