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

    Neuronpedia

    INDEX
    Explanations

    programming arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	part
    -0.08
    	top
    -0.07
    ƒ
    -0.07
     Châu
    -0.07
    larla
    -0.07
    .operation
    -0.06
     Kok
    -0.06
     Ras
    -0.06
     Cor
    -0.06
     onResume
    -0.06
    POSITIVE LOGITS
    лося
    0.06
     lucky
    0.06
    (MethodImplOptions
    0.06
     angels
    0.06
     приблиз
    0.06
    辅
    0.06
    apyrus
    0.06
    .au
    0.06
    ogenerated
    0.06
    odka
    0.06
    Act Density 0.035%

    No Known Activations