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

    Neuronpedia

    INDEX
    Explanations

    greetings

    np_max-act · gemini-2.0-flash

    polite assistant closing/offers to help (phrases like “let me know if you have any questions”).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     그냥
    -0.07
    |#
    -0.07
    NO
    -0.06
    |M
    -0.06
    𫇭
    -0.06
    输出
    -0.06
     Pen
    -0.06
     Var
    -0.06
    .description
    -0.06
    ถน
    -0.06
    POSITIVE LOGITS
    (geometry
    0.07
    (phase
    0.07
     sequencing
    0.07
    .creation
    0.07
     eclips
    0.07
     Comics
    0.06
    twor
    0.06
    PELL
    0.06
    _FREQUENCY
    0.06
     orderly
    0.06
    Act Density 0.345%

    No Known Activations