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

    Neuronpedia

    INDEX
    Explanations

    plugin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    院院士
    -0.07
     minValue
    -0.07
     enfer
    -0.07
    TT
    -0.07
    alloc
    -0.07
    mer
    -0.06
     cry
    -0.06
     patients
    -0.06
    plot
    -0.06
     Resort
    -0.06
    POSITIVE LOGITS
    ...,
    0.08
    _definition
    0.08
     века
    0.08
    :.
    0.07
    आ
    0.07
    covered
    0.07
    图案
    0.07
     Creed
    0.07
    生产的
    0.07
    	do
    0.07
    Act Density 0.000%

    No Known Activations