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

    Neuronpedia

    INDEX
    Explanations

    expectations and realism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IG
    0.61
    ise
    0.50
    ch
    0.49
    ig
    0.49
    IDS
    0.44
    f
    0.44
    IX
    0.44
    IST
    0.43
    GR
    0.43
    IE
    0.42
    POSITIVE LOGITS
     wrześ
    0.53
    тоў
    0.49
     đồng
    0.47
     ľudí
    0.47
    မဲ့
    0.47
    popupButton
    0.46
     productColor
    0.45
    တယ်
    0.45
     LoginPage
    0.45
     latérales
    0.44
    Act Density 0.002%

    No Known Activations