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

    Neuronpedia

    INDEX
    Explanations

    is a or is spelled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.38
     and
    1.18
     actin
    1.17
     predecessors
    1.16
     einiger
    1.11
     Haha
    1.08
     uzyska
    1.08
     izay
    1.06
     volna
    1.03
     starch
    1.00
    POSITIVE LOGITS
    ри
    1.57
    ATION
    1.27
    ov
    1.22
    ten
    1.22
    ❂
    1.19
    ale
    1.17
    ﹂
    1.15
    ु
    1.13
    zony
    1.13
    INGS
    1.12
    Act Density 0.274%

    No Known Activations