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

    Neuronpedia

    INDEX
    Explanations

    as such, I cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jejich
    0.55
     leurs
    0.52
     anciennes
    0.52
    }
    0.52
    OLYBD
    0.51
     ativos
    0.50
     ৪
    0.50
     especiales
    0.49
    IRCONIUM
    0.48
     rougeâtres
    0.48
    POSITIVE LOGITS
     in
    0.56
     can
    0.54
    ის
    0.52
    ні
    0.51
     have
    0.50
    G
    0.49
    ಗಳನ್ನು
    0.49
    ના
    0.48
     two
    0.48
     microphone
    0.47
    Act Density 0.329%

    No Known Activations