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

    Neuronpedia

    INDEX
    Explanations

    code copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IE
    -0.07
    blur
    -0.07
     clique
    -0.07
     شار
    -0.07
     Fortune
    -0.07
    ]))
    -0.07
     racked
    -0.07
    INTERFACE
    -0.06
     Berkeley
    -0.06
     Praha
    -0.06
    POSITIVE LOGITS
     español
    0.06
     режим
    0.06
     yield
    0.06
    cur
    0.06
     demokrat
    0.06
     yields
    0.06
    ينات
    0.06
    ヽ
    0.06
    латы
    0.06
    icans
    0.06
    Act Density 0.000%

    No Known Activations