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

    Neuronpedia

    INDEX
    Explanations

    Articles "a" and "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Baby
    -0.07
    _mapped
    -0.07
    юсь
    -0.07
    ,cljs
    -0.07
    ?'
    -0.07
    rupt
    -0.07
    label
    -0.07
      ↵
    -0.06
    (class
    -0.06
     -(
    -0.06
    POSITIVE LOGITS
     Anthrop
    0.07
    _keeper
    0.06
    ximo
    0.06
    .boolean
    0.06
    อ
    0.06
    辑
    0.05
    另一
    0.05
    Side
    0.05
    anceled
    0.05
     territories
    0.05
    Act Density 0.015%

    No Known Activations