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

    Neuronpedia

    INDEX
    Explanations

    defines by negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     այդ
    0.52
     Critique
    0.49
    این
    0.48
     itching
    0.48
     Букмекер
    0.46
     photometry
    0.46
     Tets
    0.46
     Букмекерлар
    0.46
     Annapolis
    0.46
     подроб
    0.45
    POSITIVE LOGITS
    g
    0.49
    v
    0.46
     v
    0.44
     CEO
    0.43
    alpha
    0.42
    x
    0.42
     alpha
    0.39
    F
    0.39
    ла
    0.39
    atlar
    0.39
    Act Density 0.002%

    No Known Activations