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

    Neuronpedia

    INDEX
    Explanations

    public relations and press releases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.64
     Câu
    0.55
     Hb
    0.54
     життя
    0.53
     Did
    0.52
     NaOH
    0.52
     A
    0.51
     питання
    0.49
     But
    0.49
     You
    0.49
    POSITIVE LOGITS
    s
    0.91
    8
    0.75
    4
    0.74
     announcement
    0.72
     अनाउंस
    0.68
    public
    0.67
    ق
    0.65
    ی
    0.64
    3
    0.63
    6
    0.63
    Act Density 0.059%

    No Known Activations