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

    Neuronpedia

    INDEX
    Explanations

    units of measure ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.36
     erroneous
    0.36
    flowing
    0.33
     momentary
    0.32
     noticeable
    0.31
    ઠળ
    0.31
    धित
    0.30
     an
    0.29
    pathetic
    0.29
    ými
    0.29
    POSITIVE LOGITS
     designee
    0.42
    ។
    0.39
    💪
    0.38
     Gründung
    0.37
    ）
    0.37
    。
    0.37
     APIDC
    0.36
     CORPER
    0.36
    unteer
    0.36
    ։
    0.36
    Act Density 0.234%

    No Known Activations