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

    Neuronpedia

    INDEX
    Explanations

    surreal

    np_max-act · gemini-2.0-flash

    formal or technical vocabulary, particularly medical terms and capitalized words that carry semantic importance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @rguan72
    New Auto-Interp
    Negative Logits
     qu
    -0.58
    kowitz
    -0.58
    qu
    -0.58
     kv
    -0.56
    raj
    -0.52
    kv
    -0.48
    cid
    -0.48
     sur
    -0.48
    rom
    -0.47
     form
    -0.47
    POSITIVE LOGITS
     propOrder
    0.92
    tagHelperRunner
    0.72
     Negra
    0.71
     мәкал
    0.71
     Sandstone
    0.70
    InjectAttribute
    0.70
    parsedMessage
    0.70
    RenderAtEndOf
    0.70
     Económica
    0.69
    IGraphics
    0.69
    Act Density 0.009%

    No Known Activations