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

    Neuronpedia

    INDEX
    Explanations

    translate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fun
    -0.08
     fetchData
    -0.07
     dun
    -0.07
     sanctioned
    -0.07
     Outcome
    -0.06
     endured
    -0.06
     bats
    -0.06
    _FAILED
    -0.06
     lif
    -0.06
    GetData
    -0.06
    POSITIVE LOGITS
    译
    0.07
    Player
    0.07
    حضور
    0.07
    中药材
    0.07
    IEEE
    0.07
    ==(
    0.07
     );↵
    0.07
    _before
    0.07
     básico
    0.06
    兵
    0.06
    Act Density 0.002%

    No Known Activations