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

    Neuronpedia

    INDEX
    Explanations

    code and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onic
    0.72
    imize
    0.70
    erca
    0.69
    imately
    0.69
    inte
    0.69
    all
    0.68
    from
    0.67
    imizin
    0.66
    una
    0.65
     quos
    0.65
    POSITIVE LOGITS
    龺
    0.93
    ీ
    0.92
     Định
    0.91
     Hello
    0.89
    礽
    0.86
     Länge
    0.86
     dibujar
    0.86
     Labrenzia
    0.86
     SIINFEKL
    0.86
    メリカ
    0.85
    Act Density 0.302%

    No Known Activations