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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kurds
    -0.09
     Nim
    -0.08
     Covent
    -0.08
     Gundam
    -0.07
    altern
    -0.07
    二二
    -0.07
    Popup
    -0.07
     kc
    -0.07
    _patterns
    -0.07
    presso
    -0.06
    POSITIVE LOGITS
     vời
    0.07
     distinguishing
    0.07
     pragmatic
    0.06
     power
    0.06
     입력
    0.06
    20
    0.06
    我们
    0.06
    200
    0.06
     requires
    0.06
     ello
    0.06
    Act Density 0.001%

    No Known Activations