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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Differences
    0.49
     Disorders
    0.47
     Beneficial
    0.46
    有効
    0.46
     Tasks
    0.45
    uteen
    0.43
     Enh
    0.43
     Scale
    0.42
     انتہائی
    0.42
    有所
    0.42
    POSITIVE LOGITS
     suited
    1.03
    suited
    0.93
     quality
    0.92
     odds
    0.86
     qualité
    0.85
     performers
    0.85
     качество
    0.85
     fit
    0.82
     choix
    0.82
     choices
    0.82
    Act Density 0.292%

    No Known Activations