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

    Neuronpedia

    INDEX
    Explanations

    stages, procedures, outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **
    0.77
    Read
    0.71
     Read
    0.64
    A
    0.63
    a
    0.61
    Amendment
    0.61
    **.
    0.58
    )**
    0.58
    Af
    0.57
    ạ
    0.57
    POSITIVE LOGITS
     sembra
    0.88
     begin
    0.85
    lamak
    0.83
     produc
    0.82
    MakeRect
    0.82
    ক্ক
    0.81
     subtract
    0.79
     trellis
    0.79
    ეგის
    0.78
     ആദ്യം
    0.78
    Act Density 0.116%

    No Known Activations