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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onson
    0.69
    Nak
    0.67
    Assign
    0.65
    庚
    0.63
     assign
    0.62
     পোস্টে
    0.62
    ੌਰ
    0.62
     accred
    0.61
     indenture
    0.61
    oprol
    0.61
    POSITIVE LOGITS
     variable
    1.31
    变量
    1.25
     variables
    1.24
    変数
    1.21
     Variable
    1.16
    variable
    1.14
    Variable
    1.13
     Variables
    1.06
    Variables
    1.05
     variabili
    1.04
    Act Density 0.092%

    No Known Activations