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

    Neuronpedia

    INDEX
    Explanations

    enrolled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (author
    -0.07
    OLUTE
    -0.07
     shield
    -0.06
    кость
    -0.06
    hosts
    -0.06
     RK
    -0.06
    ,col
    -0.06
    oscope
    -0.06
     grit
    -0.06
     слова
    -0.06
    POSITIVE LOGITS
     tmpl
    0.07
     userProfile
    0.07
    Except
    0.06
    ModifiedDate
    0.06
    Jerry
    0.06
     Except
    0.06
    usra
    0.06
     Asking
    0.06
    emmel
    0.06
     Тому
    0.06
    Act Density 0.005%

    No Known Activations