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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.93
    новниш
    -0.67
    脚注の使い方
    -0.66
     виправивши
    -0.65
    økt
    -0.63
    تقاوى
    -0.63
    InputTagHelper
    -0.60
    ربای
    -0.60
    URLException
    -0.60
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
     animals
    0.65
     insects
    0.58
     plants
    0.55
     body
    0.54
     bugs
    0.52
     prisoners
    0.52
     trees
    0.51
     creatures
    0.50
     animal
    0.50
    Animals
    0.49
    Act Density 0.009%

    No Known Activations