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

    Neuronpedia

    INDEX
    Explanations

    convert percentage, units, or formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overhe
    0.43
    一定会
    0.42
     Auger
    0.42
     identificado
    0.41
     nichts
    0.40
     anthracene
    0.40
     появляются
    0.40
     zwięks
    0.40
     प्रश्‍न
    0.39
    霎
    0.39
    POSITIVE LOGITS
    В
    0.47
    o
    0.46
    COMP
    0.43
    unks
    0.43
    #
    0.42
    Absolute
    0.41
    データを
    0.40
    :#
    0.40
     نوشت
    0.40
    e
    0.40
    Act Density 0.001%

    No Known Activations