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

    Neuronpedia

    INDEX
    Explanations

    start of document markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATED
    0.88
    ATING
    0.87
    ILD
    0.82
    ENSE
    0.81
     Recognizing
    0.81
     milliliters
    0.80
    shown
    0.79
     बढ़िया
    0.78
     recognising
    0.78
    ducted
    0.78
    POSITIVE LOGITS
    al
    1.12
    ography
    1.01
    age
    0.98
    ism
    0.94
    ação
    0.94
    i
    0.92
    ી
    0.90
     Hull
    0.89
    iop
    0.88
     Inggris
    0.88
    Act Density 0.000%

    No Known Activations