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

    Neuronpedia

    INDEX
    Explanations

    logical consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्रेड
    0.40
     ప్
    0.40
    知道了
    0.39
    貸款
    0.38
     ܗ
    0.38
     ర
    0.38
    gery
    0.38
     জায়
    0.38
     záp
    0.37
    insertCell
    0.37
    POSITIVE LOGITS
     isometric
    0.41
     collective
    0.39
    collective
    0.38
     slurry
    0.38
     demographic
    0.38
     quarrel
    0.38
     represents
    0.38
     aesthetic
    0.38
     dissolved
    0.37
     fermented
    0.37
    Act Density 0.001%

    No Known Activations