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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    форм
    -0.07
     MAS
    -0.06
     triggers
    -0.06
    criptors
    -0.06
    прав
    -0.06
    arbon
    -0.06
     doom
    -0.06
     facto
    -0.06
     layouts
    -0.06
    cal
    -0.06
    POSITIVE LOGITS
     temiz
    0.07
    EmptyEntries
    0.07
     ￥
    0.06
    .IsValid
    0.06
     FString
    0.06
    '),↵↵
    0.06
    。↵
    0.06
     bibliography
    0.06
     still
    0.06
     violently
    0.06
    Act Density 0.031%

    No Known Activations