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

    Neuronpedia

    INDEX
    Explanations

    location descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pamela
    -0.07
    aptcha
    -0.07
     Instagram
    -0.07
    .filename
    -0.07
    Markdown
    -0.06
     timeline
    -0.06
     Gilles
    -0.06
     previews
    -0.06
     centers
    -0.06
    حد
    -0.06
    POSITIVE LOGITS
    uzz
    0.07
    átek
    0.06
     розрах
    0.06
     Bulletin
    0.06
    ró
    0.06
     xe
    0.06
    uff
    0.06
    mpz
    0.06
    틴
    0.06
     outsider
    0.06
    Act Density 0.133%

    No Known Activations