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

    Neuronpedia

    INDEX
    Explanations

    que

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     >(
    -0.07
     excessively
    -0.07
     effect
    -0.07
    ustomed
    -0.07
    -0.07
    _option
    -0.06
     ему
    -0.06
    Suddenly
    -0.06
    ену
    -0.06
    >I
    -0.06
    POSITIVE LOGITS
     مون
    0.07
     overlapping
    0.07
     Slovak
    0.06
     aerospace
    0.06
    lifting
    0.06
    оит
    0.06
    CppGenericClass
    0.06
    NC
    0.06
    reib
    0.06
    VK
    0.05
    Act Density 0.034%

    No Known Activations