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

    Neuronpedia

    INDEX
    Explanations

    numerical data, especially in contact information and operational details

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

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➯
    -0.66
     Roskov
    -0.65
     betweenstory
    -0.53
    AxisSize
    -0.49
     rhestr
    -0.48
    ussis
    -0.48
     Administrativna
    -0.48
     дописавши
    -0.46
    tanooga
    -0.46
    InjectAttribute
    -0.45
    POSITIVE LOGITS
    ╔
    0.40
     rejected
    0.37
    Unable
    0.34
     heads
    0.34
     misses
    0.33
     clean
    0.33
    ">${
    0.33
    ;#
    0.32
    KommentareTeilen
    0.32
    rejected
    0.32
    Act Density 0.053%

    No Known Activations