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

    Neuronpedia

    INDEX
    Explanations

    understanding descriptions and automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    子
    0.47
    โม
    0.45
     lamp
    0.44
    เม
    0.43
    鮒
    0.42
    ลา
    0.42
    נג
    0.42
     snowman
    0.41
    桉
    0.41
     koy
    0.41
    POSITIVE LOGITS
     residuos
    0.61
     réforme
    0.55
     liées
    0.51
     sacrificed
    0.50
    verters
    0.50
     transporte
    0.50
     déchets
    0.50
     appreciates
    0.50
     deles
    0.49
    prices
    0.49
    Act Density 0.000%

    No Known Activations