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

    Neuronpedia

    INDEX
    Explanations

    funding rounds, especially professional boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplistic
    0.44
     lowered
    0.43
    Minimized
    0.42
     aerodynamics
    0.40
     crystallinity
    0.40
     arrogance
    0.40
    minim
    0.40
    CHANGED
    0.40
    t
    0.40
     unsatisfactory
    0.40
    POSITIVE LOGITS
     planis
    0.46
    reportBody
    0.45
    土地
    0.45
     nyata
    0.44
    랜드
    0.41
    ‍
    0.41
    为一个
    0.40
    imantan
    0.40
    يو
    0.40
    قرار
    0.40
    Act Density 0.017%

    No Known Activations