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

    Neuronpedia

    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umnos
    -0.07
    stants
    -0.07
    iterr
    -0.07
     Sav
    -0.06
    bstract
    -0.06
    uploaded
    -0.06
    ัตว
    -0.06
    ATAL
    -0.06
     листь
    -0.06
    ducible
    -0.06
    POSITIVE LOGITS
    ragen
    0.07
     změny
    0.06
     Dude
    0.06
    .prob
    0.06
    нес
    0.06
     Mus
    0.06
     PIE
    0.06
    OptionsResolver
    0.06
     ode
    0.06
    ‰
    0.06
    Act Density 0.001%

    No Known Activations