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

    Neuronpedia

    INDEX
    Explanations

    async Task;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buon
    0.73
     ther
    0.73
     h
    0.72
    na
    0.71
     people
    0.70
     $\
    0.69
     disc
    0.69
     incendi
    0.68
     lim
    0.68
    head
    0.68
    POSITIVE LOGITS
    êtres
    0.96
    <unused731>
    0.96
    एक
    0.90
    kében
    0.90
    âns
    0.89
    Derived
    0.89
    Inher
    0.88
    ငန်း
    0.87
    ప్త
    0.86
    <unused525>
    0.86
    Act Density 0.001%

    No Known Activations