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

    Neuronpedia

    INDEX
    Explanations

    subscripted variables and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sc
    0.40
    Capital
    0.40
     Sc
    0.38
     Ger
    0.37
    目安
    0.37
    Ger
    0.36
    τική
    0.36
    फा
    0.36
     prototype
    0.36
    Crystal
    0.35
    POSITIVE LOGITS
     n
    1.10
     k
    0.86
    ｎ
    0.79
    𝑛
    0.75
     N
    0.72
     nth
    0.70
     ن
    0.67
     ν
    0.59
    n
    0.58
     ন
    0.57
    Act Density 0.025%

    No Known Activations