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

    Neuronpedia

    INDEX
    Explanations

    listing categories or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     светло
    0.46
     говорю
    0.46
    >∈</
    0.45
     එක
    0.44
     되는
    0.43
     שלי
    0.42
     полицей
    0.42
    되는
    0.41
     invigorating
    0.41
    在该
    0.41
    POSITIVE LOGITS
     incorrectly
    0.48
    Το
    0.42
     Το
    0.41
     sua
    0.41
     espera
    0.40
    くれます
    0.40
    needs
    0.39
     animale
    0.39
    cluso
    0.39
     altre
    0.39
    Act Density 0.001%

    No Known Activations