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

    Neuronpedia

    INDEX
    Explanations

    new items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    decoration
    0.46
    automation
    0.46
    ావ
    0.46
    atok
    0.44
    lead
    0.44
     guill
    0.44
    lim
    0.44
    animation
    0.44
    agility
    0.44
    Scheduler
    0.43
    POSITIVE LOGITS
    人が
    0.46
     nuovo
    0.45
    한다고
    0.45
     scienza
    0.45
    NEW
    0.44
     nuova
    0.44
     Truss
    0.43
     viaggi
    0.43
     vide
    0.42
     трудно
    0.42
    Act Density 0.000%

    No Known Activations