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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生病
    -0.07
     resistor
    -0.07
    /swagger
    -0.07
     ripple
    -0.07
    Gener
    -0.07
    временно
    -0.07
    مستشار
    -0.06
    referrer
    -0.06
     Cv
    -0.06
    /remove
    -0.06
    POSITIVE LOGITS
    FileChooser
    0.07
    氆
    0.07
    >equals
    0.07
    ifact
    0.07
     OS
    0.06
    -la
    0.06
    树林
    0.06
     наук
    0.06
    ctal
    0.06
    丛书
    0.06
    Act Density 0.015%

    No Known Activations