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

    Neuronpedia

    INDEX
    Explanations

    {{

    np_max-act · gemini-2.0-flash

    The neuron activates on template‐style variable interpolation markers (the “{{” and “}}” braces) indicating embedded expressions in markup.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    b
    -0.07
     Rath
    -0.07
     lamb
    -0.07
    ard
    -0.07
    landscape
    -0.07
    Ｂ
    -0.07
    Kind
    -0.07
     Child
    -0.07
    glyph
    -0.07
    .sd
    -0.07
    POSITIVE LOGITS
     {{
    0.09
    >{{
    0.08
    /{{
    0.07
    ="{{
    0.07
     {{↵
    0.07
    licken
    0.07
    ('{{
    0.07
    国内
    0.07
    {{
    0.06
    omen
    0.06
    Act Density 0.006%

    No Known Activations