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

    Neuronpedia

    INDEX
    Explanations

    say "1"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    public
    1.42
     public
    1.42
    Public
    1.27
     Public
    1.24
     veřej
    1.19
     publice
    1.19
     PUBLIC
    1.13
     publique
    1.12
     pública
    1.06
     pubblica
    1.06
    POSITIVE LOGITS
     Twelve
    0.79
    Twelve
    0.74
    שט
    0.71
     twelve
    0.71
     eleven
    0.67
     Eleven
    0.66
    ण्डल
    0.65
    ১৩
    0.64
    ેચ્છ
    0.64
     ১৪
    0.64
    Act Density 0.094%

    No Known Activations