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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nina
    -0.09
     Oxford
    -0.08
     CUDA
    -0.08
     Eu
    -0.07
    英
    -0.07
     Goldberg
    -0.07
     英
    -0.07
     العملات
    -0.07
    ্ছে
    -0.07
     voorlop
    -0.07
    POSITIVE LOGITS
     holistic
    0.14
     interconnected
    0.11
    Connectivity
    0.11
     connectivity
    0.10
     Connectivity
    0.10
     दृष्ट
    0.10
     abordagem
    0.10
    relationships
    0.09
    -thinking
    0.09
     perspective
    0.09
    Act Density 0.010%

    No Known Activations