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

    Neuronpedia

    INDEX
    Explanations

    Difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Referencie
    -0.56
     Numerade
    -0.52
     scolaires
    -0.49
     renfor
    -0.48
     thérape
    -0.48
    ->___
    -0.47
     gebruikers
    -0.46
     users
    -0.45
     fermée
    -0.44
    важа
    -0.44
    POSITIVE LOGITS
     الرياضيه
    0.68
     imagining
    0.66
     CURIAM
    0.61
     FetchType
    0.59
    íncia
    0.58
     imagine
    0.57
    iastes
    0.56
    stwie
    0.56
    AddTagHelper
    0.55
    kuuta
    0.55
    Act Density 0.003%

    No Known Activations