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

    Neuronpedia

    INDEX
    Explanations

    oc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     velocidad
    -0.08
    man
    -0.07
     Genç
    -0.07
    _validator
    -0.07
     Moran
    -0.06
     satış
    -0.06
    connection
    -0.06
     mv
    -0.06
    investment
    -0.06
    IONS
    -0.06
    POSITIVE LOGITS
     succeeding
    0.07
     graphs
    0.07
     entails
    0.06
     Sorting
    0.06
    (notification
    0.06
    对方
    0.06
     REPL
    0.06
    屏幕
    0.06
    靠近
    0.06
    ываем
    0.06
    Act Density 0.001%

    No Known Activations