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

    Neuronpedia

    INDEX
    Explanations

    numeric values and special characters

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

    0- followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inghouse
    -0.41
    fin
    -0.39
    mtg
    -0.39
     fin
    -0.37
    preuve
    -0.36
    styleType
    -0.36
     financier
    -0.36
     Theodore
    -0.36
     Parla
    -0.36
     pos
    -0.35
    POSITIVE LOGITS
     zero
    0.53
    Zero
    0.48
    zero
    0.48
    libft
    0.47
     Grüsse
    0.47
     Zero
    0.46
    WithIOException
    0.46
     صفر
    0.45
     ZERO
    0.44
    Ծանոթ
    0.42
    Act Density 0.070%

    No Known Activations