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

    Neuronpedia

    INDEX
    Explanations

    joke about a neutron

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இல்
    0.47
    Carl
    0.45
     পলিপ
    0.42
    耔
    0.42
    اتو
    0.40
    ΜΑ
    0.39
     mejora
    0.38
     promedio
    0.38
    IQR
    0.38
     полю
    0.37
    POSITIVE LOGITS
     Consc
    0.37
     devastated
    0.36
     conscious
    0.36
     Necessary
    0.35
     Desen
    0.35
     swept
    0.34
     ಅಗತ್ಯ
    0.34
     necessary
    0.34
     clerk
    0.34
     imprisoned
    0.34
    Act Density 0.003%

    No Known Activations