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

    Neuronpedia

    INDEX
    Explanations

    Code/model related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jev
    -0.06
    proper
    -0.06
    tag
    -0.06
    -ing
    -0.06
     guideline
    -0.06
    Palindrome
    -0.06
     Academy
    -0.06
     camps
    -0.06
     Kristen
    -0.06
     Cinema
    -0.06
    POSITIVE LOGITS
     없다
    0.07
    pad
    0.07
     Darth
    0.06
    cancellationToken
    0.06
    iề
    0.06
    bilder
    0.06
    .nextLine
    0.06
     �
    0.06
    \Validation
    0.06
    ampling
    0.06
    Act Density 0.012%

    No Known Activations