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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the opening brace character '{'

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

    code block opening or object properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.43
    -
    -0.39
    l
    -0.38
    _
    -0.37
     Berg
    -0.36
    ill
    -0.36
     d
    -0.36
    л
    -0.35
     p
    -0.35
     l
    -0.35
    POSITIVE LOGITS
    ({
    1.92
    ({
    1.51
     ({
    1.45
    >({
    1.43
    ({"
    1.12
    ={({
    1.08
    ({'
    1.02
    ({\
    0.98
     ${({
    0.90
    (${
    0.88
    Act Density 0.021%

    No Known Activations