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

    Neuronpedia

    INDEX
    Explanations

    code, edits, and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    扱う
    0.41
    性和
    0.39
    度和
    0.39
    히려
    0.38
     হয়তো
    0.38
    मर्रा
    0.38
    栦
    0.38
    GALAD
    0.37
    리와
    0.37
     châu
    0.37
    POSITIVE LOGITS
     tersebut
    0.38
    0.38
     oraz
    0.36
    tob
    0.36
    。
    0.36
     above
    0.35
    above
    0.34
    and
    0.34
     and
    0.33
    です
    0.33
    Act Density 0.221%

    No Known Activations