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

    Neuronpedia

    INDEX
    Explanations

    years and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒐
    0.44
    𝐎
    0.43
    ඩ්
    0.42
    ॉक्स
    0.42
    𝑪
    0.41
    ዎት
    0.40
     earbuds
    0.40
    getVersion
    0.39
    必备
    0.39
    गराज
    0.39
    POSITIVE LOGITS
     inception
    0.49
     became
    0.44
     óta
    0.44
    ↵
    0.43
    에서
    0.42
    中
    0.42
     ২০১৪
    0.41
     seine
    0.41
     yılında
    0.41
     avea
    0.41
    Act Density 0.001%

    No Known Activations