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

    Neuronpedia

    INDEX
    Explanations

    cultures, parades, symptoms, unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    凑
    0.44
     inviol
    0.41
    PROOF
    0.39
    णीय
    0.38
    लीय
    0.38
    SLASH
    0.38
    (",",
    0.38
     deacon
    0.38
    ன்று
    0.37
     gooey
    0.37
    POSITIVE LOGITS
    Doctor
    0.41
    region
    0.38
     decided
    0.38
    oare
    0.37
    anguages
    0.37
    iger
    0.36
    ровал
    0.36
     Rad
    0.36
     žád
    0.36
    renders
    0.36
    Act Density 0.000%

    No Known Activations