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

    Neuronpedia

    INDEX
    Explanations

    under specific conditions or supervision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.87
    m
    0.79
    to
    0.66
     postérieures
    0.61
    на
    0.61
    сез
    0.59
    و
    0.59
     postérieure
    0.58
    z
    0.57
    م
    0.57
    POSITIVE LOGITS
     under
    1.13
    neath
    1.03
    under
    1.02
     auspices
    0.96
     purview
    0.90
    Under
    0.81
     guise
    0.78
     unter
    0.77
     bajo
    0.77
     scrutiny
    0.76
    Act Density 0.032%

    No Known Activations