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

    Neuronpedia

    INDEX
    Explanations

    deliver: services, results, messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étend
    1.08
     schwierig
    0.98
    大
    0.96
    ,.
    0.95
     as
    0.94
     be
    0.92
     capire
    0.91
     größere
    0.91
     desaparecido
    0.91
     \
    0.91
    POSITIVE LOGITS
    in
    1.33
    on
    1.20
    ant
    1.14
    ির
    1.13
    delivery
    1.11
    h
    1.09
     Delivering
    1.09
    hits
    1.05
    gis
    1.04
    it
    1.03
    Act Density 0.017%

    No Known Activations