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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iting
    -0.08
     assistance
    -0.08
     operasi
    -0.07
    operation
    -0.07
    ard
    -0.07
    ความ
    -0.07
    tors
    -0.07
    _enum
    -0.07
     connectivity
    -0.07
    isible
    -0.07
    POSITIVE LOGITS
    उस
    0.09
     भाजपा
    0.09
     עצמי
    0.09
    (optional
    0.09
     կազմակերպ
    0.09
     സംഘടിപ്പ
    0.09
    -style
    0.09
     કર્યો
    0.08
     કોંગ્રેસ
    0.08
    әы
    0.08
    Act Density 0.003%

    No Known Activations