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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastaan
    -0.92
     réguli
    -0.85
     Efq
    -0.83
     nahilalakip
    -0.80
     käytet
    -0.80
     fédé
    -0.79
     devenus
    -0.79
     décé
    -0.79
     solidified
    -0.77
     mitään
    -0.77
    POSITIVE LOGITS
     ins
    0.52
     process
    0.51
     non
    0.48
    tur
    0.47
     loss
    0.47
     chất
    0.46
     Mooney
    0.45
     extra
    0.44
    sab
    0.44
    非
    0.44
    Act Density 0.064%

    No Known Activations