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

    Neuronpedia

    INDEX
    Explanations

    [concept] [context]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Medicare
    0.49
     Eligible
    0.49
     Annu
    0.47
     Enrollment
    0.46
     steep
    0.46
     Rancho
    0.46
     Analytic
    0.45
     escapar
    0.45
     Derived
    0.45
     הער
    0.45
    POSITIVE LOGITS
    ر
    0.49
    、
    0.48
    лин
    0.48
    دون
    0.46
    Philosophy
    0.46
    、、
    0.45
    তৃত
    0.45
    ﺪ
    0.45
    τί
    0.44
    ピー
    0.44
    Act Density 0.001%

    No Known Activations