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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash

    The neuron activates on phrasing that indicates scaling or ramping up production processes (e.g. “scaled up,” “industrial production,” “for large‐scale”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    LOG
    -0.07
    .fastjson
    -0.07
     números
    -0.07
    _Select
    -0.07
    .SQLite
    -0.07
    uslim
    -0.06
    _rg
    -0.06
    .removeAttribute
    -0.06
     Needless
    -0.06
    (slug
    -0.06
    POSITIVE LOGITS
    ▲
    0.07
     battlefield
    0.07
    orestation
    0.06
     up
    0.06
     Logged
    0.06
     ji
    0.06
    گ
    0.06
     nakne
    0.06
     shaved
    0.06
     tropical
    0.06
    Act Density 0.008%

    No Known Activations