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

    Neuronpedia

    INDEX
    Explanations

    Nature journal articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    氇
    0.47
    受欢迎
    0.46
    bandSize
    0.43
    墘
    0.42
     FODC
    0.42
     Config
    0.42
     getConfig
    0.41
     드릴
    0.40
    徑
    0.40
     Airplane
    0.40
    POSITIVE LOGITS
    Nature
    0.79
     Nature
    0.78
     nature
    0.63
    Nat
    0.62
     natur
    0.60
     EMBO
    0.60
     Nat
    0.59
    nature
    0.59
     NATURE
    0.56
     Natur
    0.55
    Act Density 0.002%

    No Known Activations