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

    Neuronpedia

    INDEX
    Explanations

    learning and discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reservoirs
    0.46
    :"+
    0.45
     rec
    0.44
    ）；
    0.44
    計
    0.43
     eggs
    0.43
    ）
    0.43
    계를
    0.43
     ký
    0.42
    *'
    0.42
    POSITIVE LOGITS
    โท
    0.53
    Э
    0.50
     pointwise
    0.48
    ەش
    0.48
    وث
    0.46
    人々
    0.46
    ว่า
    0.45
     ponieważ
    0.45
    潸
    0.45
    returns
    0.44
    Act Density 0.000%

    No Known Activations