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

    Neuronpedia

    INDEX
    Explanations

    why things fly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ència
    0.39
    LOST
    0.39
     addChild
    0.39
     perte
    0.38
     underpin
    0.38
     reflectors
    0.38
     BANKS
    0.38
    ந்துக
    0.38
     ампли
    0.38
    ಬ್ಬಳ್ಳಿ
    0.38
    POSITIVE LOGITS
    ploader
    0.40
    経済
    0.38
     economy
    0.37
     현실
    0.36
     tig
    0.36
     economists
    0.36
     economist
    0.35
     engineer
    0.35
    剰
    0.35
    ption
    0.35
    Act Density 0.004%

    No Known Activations