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

    Neuronpedia

    INDEX
    Explanations

    informational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COMMIT
    -0.07
     rude
    -0.06
    ỗng
    -0.06
    (tab
    -0.06
     crim
    -0.06
     dünyada
    -0.06
    ／/
    -0.06
     공고
    -0.06
     küçük
    -0.06
     esports
    -0.06
    POSITIVE LOGITS
     informational
    0.09
     honorary
    0.07
     concert
    0.07
    وتر
    0.07
     precaution
    0.07
     explanation
    0.07
    WI
    0.07
    �
    0.06
    inks
    0.06
    ни
    0.06
    Act Density 0.002%

    No Known Activations