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

    Neuronpedia

    INDEX
    Explanations

    compound terms or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    АТ
    0.81
    ОР
    0.77
     as
    0.74
    АР
    0.74
    𝘢
    0.73
    centos
    0.73
     և
    0.72
    िनेट
    0.71
    களில்
    0.71
    代谢
    0.71
    POSITIVE LOGITS
    ou
    0.86
     I
    0.81
    ia
    0.81
        
    0.80
    （
    0.80
    )
    0.79
    ির
    0.79
    a
    0.78
    um
    0.77
    I
    0.77
    Act Density 0.355%

    No Known Activations