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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     personnes
    -0.08
    研
    -0.07
    Java
    -0.07
     infinite
    -0.06
     nurse
    -0.06
    ็น
    -0.06
    STR
    -0.06
    PMC
    -0.06
     populations
    -0.06
    وط
    -0.06
    POSITIVE LOGITS
     gore
    0.07
    _publish
    0.06
     війни
    0.06
     sedan
    0.06
     getInput
    0.06
     taller
    0.06
     power
    0.06
    Ending
    0.06
    ázal
    0.06
     grabbed
    0.06
    Act Density 0.103%

    No Known Activations