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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron activates on the date‐and‐merger sentence in former-commune articles (e.g. the “On 1 January 2017, it was merged into…” pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anim
    -0.07
    �
    -0.07
    사무
    -0.06
    (title
    -0.06
     지정
    -0.06
    Friends
    -0.06
    produto
    -0.06
    zar
    -0.06
     fair
    -0.06
    nak
    -0.06
    POSITIVE LOGITS
     archit
    0.06
    .escape
    0.06
     scaling
    0.06
    (program
    0.06
     Flexible
    0.06
     upscale
    0.06
    .borderColor
    0.06
    .hasNext
    0.06
     =↵↵
    0.06
     bolster
    0.06
    Act Density 0.011%

    No Known Activations