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

    Neuronpedia

    INDEX
    Explanations

    modelmodel/product numbers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     නමුත්
    0.30
     Lúc
    0.29
     nerdy
    0.28
     sarcasm
    0.28
    ່ວນ
    0.28
     じゃん
    0.28
     ridicule
    0.27
     humbled
    0.27
     trivia
    0.27
     sexist
    0.27
    POSITIVE LOGITS
    1
    0.39
    IS
    0.39
    2
    0.38
    II
    0.37
    ALL
    0.37
    AC
    0.37
    ID
    0.36
    IP
    0.36
    NS
    0.36
    6
    0.36
    Act Density 0.110%

    No Known Activations