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

    Neuronpedia

    INDEX
    Explanations

    variable names and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    低下
    0.66
    importanza
    0.65
    अधिका
    0.64
     suppuration
    0.64
    шее
    0.63
    ্রেক
    0.62
    ścio
    0.61
     Oldborough
    0.61
    茭
    0.61
    䳕
    0.61
    POSITIVE LOGITS
    0.85
     T
    0.76
     S
    0.74
     K
    0.74
    ↵↵
    0.73
     D
    0.73
     P
    0.72
     F
    0.72
     J
    0.71
     H
    0.71
    Act Density 0.000%

    No Known Activations