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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чем
    -0.07
    _cp
    -0.06
     Liu
    -0.06
     fatto
    -0.06
     Desde
    -0.06
    oshi
    -0.06
     الظ
    -0.06
     vrouwen
    -0.06
     NIH
    -0.06
     البي
    -0.06
    POSITIVE LOGITS
    Uuid
    0.06
    -chat
    0.06
    athan
    0.06
    _Run
    0.06
     paired
    0.06
    (Data
    0.06
    .Shared
    0.06
     ={↵
    0.06
    ,map
    0.06
    ,...
    0.06
    Act Density 0.027%

    No Known Activations