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

    Neuronpedia

    INDEX
    Explanations

    references to religious people and institutions

    oai_token-act-pair · gemini-2.0-flash

    nuns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Италијани
    -0.54
     créateur
    -0.54
     Scip
    -0.50
     Scrooge
    -0.50
     crickets
    -0.50
     trifle
    -0.49
     parlare
    -0.49
     Shaksp
    -0.48
     yanı
    -0.48
     termites
    -0.48
    POSITIVE LOGITS
    ruptedException
    0.73
    enschappelijke
    0.56
    ortun
    0.54
    styleable
    0.54
    Hentet
    0.53
    ViewImports
    0.53
    endwhile
    0.53
    ssf
    0.53
     Schal
    0.52
    URLException
    0.52
    Act Density 2.762%

    No Known Activations