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

    Neuronpedia

    INDEX
    Explanations

    Builder design pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cel
    -0.08
    Binary
    -0.08
     Alarm
    -0.07
     THEM
    -0.07
     Haar
    -0.07
     thunderstorms
    -0.07
     alarm
    -0.07
     hv
    -0.07
    hv
    -0.07
     Sloan
    -0.07
    POSITIVE LOGITS
    _builder
    0.14
     builder
    0.13
    	builder
    0.13
    \Builder
    0.13
    (builder
    0.13
     builders
    0.12
     Builder
    0.12
    -builder
    0.12
    builder
    0.11
    Builder
    0.11
    Act Density 0.003%

    No Known Activations