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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .timestamp
    -0.07
     Fle
    -0.07
     apprent
    -0.07
    ABCDEFG
    -0.07
     education
    -0.07
    SECOND
    -0.07
     EDUC
    -0.06
     relig
    -0.06
     Wilkinson
    -0.06
     Ferrari
    -0.06
    POSITIVE LOGITS
     мож
    0.06
     etkil
    0.06
     possibilities
    0.06
     fds
    0.06
    "
↵
↵
    0.06
    _menu
    0.06
    /Documents
    0.06
    ’↵↵
    0.06
    γράφ
    0.06
    Comparer
    0.06
    Act Density 0.005%

    No Known Activations