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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Computing
    -0.07
    eax
    -0.06
    Distribution
    -0.06
     �
    -0.06
     Lear
    -0.06
     roommate
    -0.06
    Ｄ
    -0.06
    615
    -0.06
     Inst
    -0.06
     Flynn
    -0.06
    POSITIVE LOGITS
    <G
    0.07
    subtitle
    0.06
    <Result
    0.06
     Frog
    0.06
    =sum
    0.06
     katıl
    0.06
    GameState
    0.06
     agricult
    0.06
    _plan
    0.06
     '''↵
    0.06
    Act Density 0.027%

    No Known Activations