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

    Neuronpedia

    INDEX
    Explanations

    financial terms and conditions related to payments and expenses

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

    separate linear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.72
    principalColumn
    -0.63
    EndContext
    -0.55
     виправивши
    -0.53
     TAMBÉM
    -0.52
    :✨
    -0.52
     kysy
    -0.48
    migrationBuilder
    -0.47
     nakalista
    -0.47
     INTERESAR
    -0.46
    POSITIVE LOGITS
    BadRequest
    0.43
     Partridge
    0.42
     Barbe
    0.41
     Maze
    0.41
    SaveChangesAsync
    0.41
    menopausal
    0.40
    MessageDigest
    0.40
    மே
    0.40
     Hann
    0.39
    posedge
    0.39
    Act Density 0.066%

    No Known Activations