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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isty
    -0.07
     Conte
    -0.06
    Введите
    -0.06
     Oscars
    -0.06
     HELP
    -0.06
    इस
    -0.06
     landsc
    -0.06
    就会
    -0.06
    RESS
    -0.06
    標
    -0.06
    POSITIVE LOGITS
    (heap
    0.08
    уда
    0.07
     HIM
    0.07
    ,password
    0.07
    увався
    0.06
    0.06
    HZ
    0.06
    abi
    0.06
    ometers
    0.06
     kültür
    0.06
    Act Density 0.000%

    No Known Activations