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

    Neuronpedia

    INDEX
    Explanations

    the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    means or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.45
     fédé
    -0.44
     usize
    -0.43
     sièges
    -0.43
     étoit
    -0.40
     cœurs
    -0.40
     bâtiment
    -0.39
     houſe
    -0.39
    filelist
    -0.39
     hạng
    -0.38
    POSITIVE LOGITS
     AssemblyCulture
    0.89
     pinulongan
    0.78
     through
    0.74
     via
    0.74
    rzez
    0.73
     attraverso
    0.71
    through
    0.71
     THROUGH
    0.71
     Chwiliwch
    0.70
    __(/*!
    0.69
    Act Density 0.026%

    No Known Activations