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

    Neuronpedia

    INDEX
    Explanations

    writing/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     folded
    -0.07
     siyas
    -0.06
    	message
    -0.06
    ीटर
    -0.06
     rapidly
    -0.06
     competition
    -0.06
     Ballard
    -0.06
     존
    -0.05
    зації
    -0.05
     по
    -0.05
    POSITIVE LOGITS
     Diagnosis
    0.08
     \<^
    0.08
    <article
    0.07
     ForCanBeConvertedToForeach
    0.07
     Spells
    0.06
     avant
    0.06
     Enter
    0.06
    ธรรม
    0.06
     Vil
    0.06
     Accepted
    0.06
    Act Density 0.006%

    No Known Activations