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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Herr
    -0.07
    antor
    -0.07
     tarde
    -0.07
    etí
    -0.06
     друга
    -0.06
    alian
    -0.06
    	LOGGER
    -0.06
    ازد
    -0.06
    rebbe
    -0.06
    くの
    -0.06
    POSITIVE LOGITS
    REDENTIAL
    0.07
    <Customer
    0.06
     เจ
    0.06
     бук
    0.06
    ）（
    0.06
    (remove
    0.06
    (filter
    0.06
    .rb
    0.06
     www
    0.06
     Specifically
    0.05
    Act Density 0.048%

    No Known Activations