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

    Neuronpedia

    INDEX
    Explanations

    research and experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    för
    -0.07
    Decor
    -0.07
    ุร
    -0.06
     abruptly
    -0.06
     至
    -0.06
    กร
    -0.06
     со
    -0.06
    istring
    -0.06
    ‌کننده
    -0.06
     discriminatory
    -0.06
    POSITIVE LOGITS
    _CT
    0.07
     RESET
    0.06
     diagn
    0.06
    ,file
    0.06
     vent
    0.06
     SVC
    0.06
    _CD
    0.06
     norm
    0.06
    alysis
    0.06
     Mag
    0.06
    Act Density 0.051%

    No Known Activations