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

    Neuronpedia

    INDEX
    Explanations

    performance on stage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     langfrist
    0.51
     supervisory
    0.43
     epidemi
    0.43
     infecciones
    0.43
     klikken
    0.42
    学習
    0.41
     juvenil
    0.40
     Guilherme
    0.40
    短期
    0.40
    規模
    0.38
    POSITIVE LOGITS
     onstage
    0.98
     stage
    0.69
     backstage
    0.66
     स्टेज
    0.66
     মঞ্চ
    0.65
     performers
    0.64
     performer
    0.64
     मंच
    0.64
    观众
    0.62
    表演
    0.62
    Act Density 0.053%

    No Known Activations