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

    Neuronpedia

    INDEX
    Explanations

    parts of Dutch names for organizations

    oai_token-act-pair · gemini-2.0-flash

    Code/technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    balt
    -0.54
     Bioaccumulative
    -0.53
    Battery
    -0.52
     chevalier
    -0.50
    Batis
    -0.48
    featureID
    -0.48
    bateria
    -0.48
     ๆ
    -0.47
    albero
    -0.47
    şağı
    -0.47
    POSITIVE LOGITS
    ########.
    0.80
    rungsseite
    0.52
     <<<<<<<<<<<<<<
    0.47
     IMDB
    0.47
     Wikispecies
    0.47
     transcript
    0.47
     upgra
    0.44
     Pellegrini
    0.44
     gyrus
    0.44
    ProgressHUD
    0.43
    Act Density 0.160%

    No Known Activations