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

    Neuronpedia

    INDEX
    Explanations

    sender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harb
    -0.07
     impunity
    -0.07
     Crisis
    -0.07
    Eval
    -0.06
    Fuck
    -0.06
    ighb
    -0.06
     window
    -0.06
     номер
    -0.06
    Wrong
    -0.06
     конкрет
    -0.06
    POSITIVE LOGITS
    .InnerException
    0.07
     aerial
    0.07
    .travel
    0.07
     bois
    0.06
     TempData
    0.06
     ))↵
    0.06
     करत
    0.06
     ).↵
    0.06
    -install
    0.06
    .tintColor
    0.06
    Act Density 0.069%

    No Known Activations