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

    Neuronpedia

    INDEX
    Explanations

    reducing weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     site
    0.41
     realizzazione
    0.41
    ąda
    0.40
    رك
    0.38
     realização
    0.38
     mergeddata
    0.38
    િલ
    0.38
     tako
    0.37
     mastic
    0.37
     operazioni
    0.37
    POSITIVE LOGITS
     নাঁ
    0.44
    魇
    0.42
    回头
    0.42
    street
    0.42
    app
    0.41
     書い
    0.41
    เร
    0.40
    crum
    0.40
    unitary
    0.40
    xiety
    0.40
    Act Density 0.000%

    No Known Activations