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

    Neuronpedia

    INDEX
    Explanations

    broadcast, irradiate, traditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hinder
    0.46
    雛
    0.41
     nymph
    0.41
    st
    0.40
     brood
    0.40
     acutely
    0.39
     estate
    0.39
    s
    0.39
     أبر
    0.39
     ostatnich
    0.39
    POSITIVE LOGITS
    ามารถ
    0.46
    ที่จะ
    0.46
     accompagné
    0.45
    ﺓ
    0.44
     Incentive
    0.43
     Programs
    0.43
     जोकि
    0.43
    PPI
    0.42
    牷
    0.42
    ጋገብ
    0.42
    Act Density 0.001%

    No Known Activations