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

    Neuronpedia

    INDEX
    Explanations

    had

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.33
    been
    0.29
    is
    0.28
    o
    0.28
    chalk
    0.27
    е
    0.27
    ed
    0.27
    on
    0.27
    id
    0.27
    ir
    0.27
    POSITIVE LOGITS
     Ā
    0.28
     челове
    0.28
     Melanes
    0.28
     принцип
    0.27
     മനുഷ്യ
    0.26
     Nā
    0.26
     Με
    0.26
    <unused689>
    0.26
     पेशेवर
    0.26
     Kek
    0.26
    Act Density 0.003%

    No Known Activations