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

    Neuronpedia

    INDEX
    Explanations

    gravity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oneofs
    -0.73
    tableFuture
    -0.68
    extAlignment
    -0.62
     ++)
    -0.62
     كومونز
    -0.61
     BoxFit
    -0.60
    oyer
    -0.60
    IndentedString
    -0.58
    UpInside
    -0.58
    PreferredItem
    -0.58
    POSITIVE LOGITS
     gesucht
    0.49
     isolé
    0.49
    sidemargin
    0.49
     spéciaux
    0.46
     indisponible
    0.45
     personnelle
    0.45
     samtidigt
    0.44
     extérieures
    0.43
     celé
    0.43
     mentiras
    0.42
    Act Density 0.003%

    No Known Activations