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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in code or documentation

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

    code transformation and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.57
    Jîn
    -0.49
    Tikang
    -0.49
    Hauptartikel
    -0.48
    AnimationsModule
    -0.45
     desmotivaciones
    -0.43
    AutoField
    -0.43
    ckså
    -0.43
    DockStyle
    -0.43
     calcetines
    -0.41
    POSITIVE LOGITS
     Pala
    0.47
     Mills
    0.44
     CallOverrides
    0.41
    edu
    0.41
     Tok
    0.40
    yng
    0.39
     Edu
    0.39
    Mills
    0.39
     edu
    0.39
     Pier
    0.39
    Act Density 0.005%

    No Known Activations