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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aders
    -0.07
     investors
    -0.07
     출장
    -0.07
     smarter
    -0.06
     COOKIE
    -0.06
    Margin
    -0.06
    ElapsedTime
    -0.06
     Properties
    -0.06
    овах
    -0.06
    ファ
    -0.06
    POSITIVE LOGITS
    /up
    0.07
    .getNode
    0.06
     Wage
    0.06
    .Bit
    0.06
     sdl
    0.06
    .");
↵
    0.06
     एज
    0.06
    нен
    0.06
    _CSR
    0.06
     =(
    0.06
    Act Density 0.010%

    No Known Activations