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

    Neuronpedia

    INDEX
    Explanations

    scientific language and technical terms related to experiments, measurements, and analysis

    oai_token-act-pair · gemini-2.0-flash

    experimental procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.60
    UserScript
    -0.54
    RectangleBorder
    -0.49
    हाय
    -0.49
     Multipart
    -0.45
    ToRefresh
    -0.45
    HttpPost
    -0.44
     CURI
    -0.44
    кото
    -0.44
    ]++;
    -0.43
    POSITIVE LOGITS
     using
    1.20
     keeping
    1.09
     taking
    0.99
     utilizing
    0.95
     используя
    0.94
     putting
    0.91
     assuming
    0.91
     USING
    0.90
     ignoring
    0.89
     letting
    0.88
    Act Density 2.312%

    No Known Activations