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

    Neuronpedia

    INDEX
    Explanations

    Recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhà
    -0.07
     moderated
    -0.07
    privacy
    -0.07
    .beh
    -0.07
    ٬
    -0.06
     ton
    -0.06
    .C
    -0.06
    ูท
    -0.06
     attenuation
    -0.06
     iy
    -0.06
    POSITIVE LOGITS
    _FORCE
    0.06
     spoken
    0.06
     ustanovení
    0.06
     Creates
    0.06
     integrates
    0.06
     '{@
    0.06
    /*!↵
    0.06
    (handler
    0.06
    .TestCheck
    0.06
     Body
    0.06
    Act Density 0.010%

    No Known Activations