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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Enter
    -0.07
    ifornia
    -0.07
     Melania
    -0.07
    athon
    -0.07
     Wikimedia
    -0.07
    IVEN
    -0.07
     Scandin
    -0.06
    ISO
    -0.06
    ahas
    -0.06
     Hulu
    -0.06
    POSITIVE LOGITS
     cartridge
    0.07
    	button
    0.07
     paradigm
    0.07
     agréable
    0.06
     שכל
    0.06
     credibility
    0.06
    谴
    0.06
     pellets
    0.06
     priority
    0.06
    岭
    0.06
    Act Density 0.025%

    No Known Activations