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

    Neuronpedia

    INDEX
    Explanations

    accelerated aging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.66
    i
    0.52
     Yours
    0.47
     Over
    0.44
     Stand
    0.44
     Please
    0.43
     All
    0.43
     Gu
    0.43
    measure
    0.43
     Hope
    0.43
    POSITIVE LOGITS
    eren
    0.55
    éroport
    0.54
    ígono
    0.52
    ímica
    0.51
    ဟာ
    0.51
    깥
    0.51
    eric
    0.50
    fireFlower
    0.50
     совпада
    0.49
     uç
    0.49
    Act Density 0.000%

    No Known Activations