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

    Neuronpedia

    INDEX
    Explanations

    causal or indicative phrases that signify conclusions or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indicates consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.66
     Wiktionnaire
    -0.59
    +#+#
    -0.59
     AssemblyCompany
    -0.56
     snippetHide
    -0.52
     ***!
    -0.51
    intios
    -0.51
    afficheront
    -0.50
     extérieur
    -0.48
    ########.
    -0.48
    POSITIVE LOGITS
     which
    0.48
     WHICH
    0.46
    which
    0.45
     Which
    0.40
     vlast
    0.37
     weshalb
    0.35
     مما
    0.35
    Which
    0.34
     femininas
    0.34
     vilket
    0.33
    Act Density 0.066%

    No Known Activations