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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    166
    -0.07
    roach
    -0.06
     Sept
    -0.06
    876
    -0.06
    >;
↵
    -0.06
    979
    -0.06
     OR
    -0.06
    alion
    -0.06
    385
    -0.06
    ">
    -0.06
    POSITIVE LOGITS
    HBoxLayout
    0.07
     payable
    0.06
    -panel
    0.06
     dược
    0.06
     Thị
    0.06
    (abs
    0.06
    grund
    0.06
     gameId
    0.06
     brides
    0.06
     offend
    0.06
    Act Density 0.021%

    No Known Activations