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

    Neuronpedia

    INDEX
    Explanations

    ebooks guides papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
↵
    -0.08
    /security
    -0.07
    екар
    -0.07
     tracing
    -0.06
    appear
    -0.06
     principalColumn
    -0.06
     GeForce
    -0.06
    (scope
    -0.06
    (speed
    -0.06
     Cleanup
    -0.06
    POSITIVE LOGITS
     Progress
    0.06
     TForm
    0.06
    .fetchall
    0.06
     chuck
    0.06
     Mod
    0.06
     uniqu
    0.06
     Minute
    0.06
    くと
    0.06
     filib
    0.06
     &&
    0.06
    Act Density 0.044%

    No Known Activations