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

    Neuronpedia

    INDEX
    Explanations

    say German "Überblick" or "Leit"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     store
    -0.10
     integration
    -0.09
    ibs
    -0.09
    competition
    -0.09
     name
    -0.09
     leute
    -0.09
    reservation
    -0.09
     største
    -0.09
     nodige
    -0.09
    antiation
    -0.09
    POSITIVE LOGITS
     Bestandteil
    0.15
     Qualitäts
    0.14
     Positions
    0.14
     Maßnahmen
    0.13
     Are
    0.13
     Empfehl
    0.13
     Zahlen
    0.12
     Fun
    0.12
     Motiv
    0.12
     Inspirations
    0.12
    Act Density 0.011%

    No Known Activations