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

    Neuronpedia

    INDEX
    Explanations

    proposals and suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilize
    0.50
     utilise
    0.47
     utilizado
    0.46
     utilizada
    0.45
     используется
    0.45
     využ
    0.44
     используются
    0.43
     utilización
    0.43
    follow
    0.43
     menjalani
    0.43
    POSITIVE LOGITS
     prepared
    0.80
     proposes
    0.79
     proposing
    0.79
     proposent
    0.74
     propose
    0.74
    を用意
    0.74
     propone
    0.71
     propon
    0.71
     presents
    0.70
     предлага
    0.69
    Act Density 0.014%

    No Known Activations