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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Retirement
    -0.06
    ana
    -0.06
    �
    -0.06
    era
    -0.06
     Slo
    -0.06
    िसस
    -0.06
    انا
    -0.06
    BEGIN
    -0.06
    άνα
    -0.06
    girls
    -0.06
    POSITIVE LOGITS
     Architect
    0.11
     architect
    0.11
     Architecture
    0.11
     architecture
    0.10
     archit
    0.09
     طر
    0.08
    itect
    0.08
     architects
    0.08
     structure
    0.08
    architecture
    0.07
    Act Density 0.013%

    No Known Activations