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

    Neuronpedia

    INDEX
    Explanations

    caliber

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.66
     derivatives
    -0.65
     caliber
    -0.65
     Derivatives
    -0.63
    s
    -0.62
     calibre
    -0.60
     privately
    -0.57
    slash
    -0.56
    ConstraintMaker
    -0.56
     ujednoznacz
    -0.55
    POSITIVE LOGITS
     provisoire
    0.56
     fallait
    0.55
    Schicken
    0.54
    latego
    0.53
     useAuth
    0.53
     rallado
    0.52
     intérieure
    0.50
    untura
    0.50
     Kars
    0.50
     magique
    0.49
    Act Density 0.364%

    No Known Activations