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

    Neuronpedia

    INDEX
    Explanations

    Sea, Oxygen, Cortex, perox

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.71
    f
    0.66
    a
    0.63
    st
    0.55
    r
    0.55
    pa
    0.54
    tt
    0.53
    o
    0.52
    provider
    0.51
    skou
    0.50
    POSITIVE LOGITS
    択
    0.57
     haies
    0.51
     판매
    0.50
     미래
    0.50
     komunik
    0.50
     배
    0.49
     социально
    0.49
     vendas
    0.49
     huevo
    0.48
     하늘
    0.48
    Act Density 0.000%

    No Known Activations