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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dizaines
    -0.67
     centaines
    -0.61
     voisins
    -0.60
     remplacement
    -0.57
     manières
    -0.55
     segítség
    -0.54
     milliers
    -0.53
     revés
    -0.52
     enfans
    -0.52
     ägg
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.87
    Tikang
    0.79
    WriteTagHelper
    0.77
    DockStyle
    0.75
    Espèce
    0.71
     <=",
    0.70
    isContained
    0.69
    DebuggerNonUser
    0.69
    出版年
    0.69
    MessageOf
    0.68
    Act Density 0.001%

    No Known Activations