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

    Neuronpedia

    INDEX
    Explanations

    improbable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lemma
    0.51
    lijke
    0.45
     फीस
    0.44
    kele
    0.43
     seasons
    0.43
     enkel
    0.43
     kettle
    0.42
    ॉक्स
    0.42
    ia
    0.42
    lasting
    0.42
    POSITIVE LOGITS
    Agar
    0.52
     Chakraborty
    0.47
     ຄ
    0.46
    鲟
    0.46
     Qxe
    0.46
     pertanto
    0.46
     PLHIV
    0.45
     Dazu
    0.45
    ຊ
    0.45
    ᱑
    0.44
    Act Density 0.001%

    No Known Activations