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

    Neuronpedia

    INDEX
    Explanations

    Session IDs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observ
    -0.07
    ampil
    -0.07
     واقعی
    -0.07
     сохра
    -0.06
     ='
    -0.06
     Reflex
    -0.06
     OPP
    -0.06
    -person
    -0.06
     leží
    -0.06
    Age
    -0.06
    POSITIVE LOGITS
    primer
    0.08
    ﾍ
    0.07
     dishonest
    0.07
     рассчит
    0.06
     mAuth
    0.06
     Premium
    0.06
     lacked
    0.06
     genius
    0.06
     tidak
    0.06
     Convenience
    0.06
    Act Density 0.013%

    No Known Activations