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

    Neuronpedia

    INDEX
    Explanations

    definitions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aea
    0.46
    one
    0.44
    원에서
    0.43
    e
    0.43
     שה
    0.43
    cado
    0.43
    letic
    0.43
     e
    0.42
    Mad
    0.42
    秝
    0.42
    POSITIVE LOGITS
     Ausbildung
    0.47
     Buku
    0.46
     Landschaft
    0.46
     ಅದರ
    0.44
     Bücher
    0.44
     svjets
    0.43
    ಂತರ
    0.43
     Antwort
    0.43
     Deutscher
    0.42
    Ώ
    0.42
    Act Density 0.101%

    No Known Activations