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

    Neuronpedia

    INDEX
    Explanations

    Numbered lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بح
    -0.07
    طف
    -0.07
    igits
    -0.06
     кишеч
    -0.06
     參
    -0.06
    JoinColumn
    -0.06
     dữ
    -0.06
    τικά
    -0.06
    -control
    -0.06
     expressions
    -0.06
    POSITIVE LOGITS
    .error
    0.07
    599
    0.06
    (hist
    0.06
    .mock
    0.06
     philosoph
    0.06
     тяжел
    0.06
     git
    0.06
     Psych
    0.06
     systemd
    0.06
     expectedResult
    0.06
    Act Density 0.005%

    No Known Activations