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

    Neuronpedia

    INDEX
    Explanations

    Own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kl
    -0.08
     pys
    -0.08
    15
    -0.07
    75
    -0.07
    kl
    -0.07
     puntual
    -0.07
    	struct
    -0.07
     solitaire
    -0.07
     pila
    -0.07
    81
    -0.07
    POSITIVE LOGITS
     controlling
    0.11
     नियंत्रण
    0.10
     controls
    0.10
     প্রশাস
    0.10
     freezing
    0.10
     प्रशासन
    0.10
     المدير
    0.09
     ಆಡ
    0.09
     CEO
    0.09
     ಅಧಿಕಾರ
    0.09
    Act Density 0.003%

    No Known Activations