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

    Neuronpedia

    INDEX
    Explanations

    predictive back gesture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     музея
    0.50
     들어
    0.49
     addressing
    0.47
     with
    0.46
     różne
    0.46
     discusses
    0.46
     recognise
    0.46
     reviewed
    0.45
     nettoy
    0.45
     bringing
    0.45
    POSITIVE LOGITS
    铛
    0.50
    జ్
    0.47
    apsingToolbar
    0.46
    ğiniz
    0.43
    ğimiz
    0.43
    ový
    0.43
    imizin
    0.43
    šky
    0.43
    ğim
    0.42
    imizi
    0.42
    Act Density 0.001%

    No Known Activations