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

    Neuronpedia

    INDEX
    Explanations

    International Corp., basic plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vera
    0.93
     Moritz
    0.90
    benzo
    0.86
     thistle
    0.86
    يره
    0.85
     Burgen
    0.83
     Martina
    0.81
     MSA
    0.80
     Rizzo
    0.79
    rü
    0.78
    POSITIVE LOGITS
     Shap
    1.05
    ンプ
    1.04
     Copeland
    0.98
     Kemp
    0.93
     Rap
    0.93
     Stap
    0.90
     Fournier
    0.90
     Lak
    0.88
    rap
    0.87
    shap
    0.87
    Act Density 0.934%

    No Known Activations