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

    Neuronpedia

    INDEX
    Explanations

    asking clarifying questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    1.48
    は
    1.38
    𝘳
    1.37
    𝘢
    1.32
    𝘭
    1.32
    й
    1.24
    一种
    1.23
    𝘦
    1.23
    إ
    1.19
    𝖒
    1.19
    POSITIVE LOGITS
     dictated
    1.16
    dominated
    1.14
     uppermost
    1.14
     incumbent
    1.11
    >;
    1.07
     ها
    1.07
    kampf
    1.07
     incumbents
    1.06
     alluded
    1.06
    ística
    1.06
    Act Density 0.252%

    No Known Activations