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

    Neuronpedia

    INDEX
    Explanations

    words that mean "easy" or "difficult"

    oai_token-act-pair · gemini-2.0-flash

    easy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -0.94
     HasFactory
    -0.73
     transfieras
    -0.73
    mybatisplus
    -0.70
     traditionnels
    -0.69
    IntoConstraints
    -0.65
    +#+
    -0.65
    GEBURTSDATUM
    -0.64
     militaires
    -0.63
     Савезне
    -0.63
    POSITIVE LOGITS
     easily
    1.34
     easy
    1.30
     Easily
    1.27
    easily
    1.26
     Easy
    1.14
    easy
    1.14
    Easily
    1.10
    Easy
    1.08
     EASY
    1.07
     easier
    1.05
    Act Density 0.912%

    No Known Activations