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

    Neuronpedia

    INDEX
    Explanations

    (+/-)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plagued
    -0.07
    으
    -0.06
     "...
    -0.06
     얘
    -0.06
     SVC
    -0.06
     diag
    -0.06
    =""
    -0.06
     Composer
    -0.06
     Registrar
    -0.06
     古
    -0.06
    POSITIVE LOGITS
     헤
    0.07
    received
    0.07
    */
↵
    0.06
    .addHandler
    0.06
    ustil
    0.06
    ServletResponse
    0.06
    IBUTES
    0.06
    тів
    0.06
     integers
    0.06
    unprocessable
    0.06
    Act Density 0.009%

    No Known Activations