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

    Neuronpedia

    INDEX
    Explanations

    mb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estination
    -0.07
    (animation
    -0.07
     cof
    -0.07
    組織
    -0.07
     duplication
    -0.07
    orrh
    -0.06
    (sort
    -0.06
     gall
    -0.06
    ercise
    -0.06
    Vals
    -0.06
    POSITIVE LOGITS
     shaping
    0.07
     innovative
    0.07
    ybrid
    0.07
    슁
    0.07
    mb
    0.07
    봇
    0.06
    夸张
    0.06
     strap
    0.06
    ович
    0.06
     MB
    0.06
    Act Density 0.008%

    No Known Activations