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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     personality
    -0.08
     pm
    -0.07
    Disc
    -0.07
    .nl
    -0.07
    E
    -0.06
    W
    -0.06
    ographical
    -0.06
    '.
    -0.06
    葉
    -0.06
    ада
    -0.06
    POSITIVE LOGITS
     금
    0.07
     Cros
    0.06
     ullam
    0.06
     имму
    0.06
    ละคร
    0.06
     showModal
    0.06
    pick
    0.06
     保
    0.06
    �
    0.06
     Generation
    0.06
    Act Density 0.009%

    No Known Activations