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

    Neuronpedia

    INDEX
    Explanations

    Census data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pressure
    -0.07
    sentence
    -0.07
     Lv
    -0.07
     quality
    -0.06
     spaceship
    -0.06
     Probably
    -0.06
     sentence
    -0.06
    ویل
    -0.06
     garg
    -0.06
    Fax
    -0.05
    POSITIVE LOGITS
     elapsedTime
    0.07
     writeFile
    0.07
    odox
    0.07
     EXCEPTION
    0.07
    촌
    0.07
     occas
    0.07
    	sig
    0.06
     Anat
    0.06
    929
    0.06
     heatmap
    0.06
    Act Density 0.004%

    No Known Activations