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

    Neuronpedia

    INDEX
    Explanations

    time and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affinity
    0.41
     bearers
    0.41
     inhibit
    0.40
     intenta
    0.40
     sensibil
    0.39
     spread
    0.39
     sparing
    0.39
     entourage
    0.39
     brethren
    0.39
     spared
    0.38
    POSITIVE LOGITS
     |.
    0.45
    kW
    0.45
     кг
    0.44
     রোববার
    0.42
    ිනි
    0.41
     …,
    0.41
     .;
    0.40
     suic
    0.39
    sudo
    0.39
    кг
    0.39
    Act Density 0.002%

    No Known Activations