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

    Neuronpedia

    INDEX
    Explanations

    Podcast transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dece
    -0.07
    	await
    -0.07
    503
    -0.06
    manager
    -0.06
    _friend
    -0.06
     offerings
    -0.06
    ipc
    -0.06
    кой
    -0.06
    =key
    -0.06
     terrific
    -0.06
    POSITIVE LOGITS
     모
    0.07
    자동
    0.06
     Certificate
    0.06
     petals
    0.06
    unordered
    0.06
     Rendering
    0.06
     offseason
    0.06
     自
    0.06
    character
    0.06
     発
    0.06
    Act Density 0.094%

    No Known Activations