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

    Neuronpedia

    INDEX
    Explanations

    elected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harmony
    -0.07
    olve
    -0.07
     Ca
    -0.07
    ourd
    -0.06
     исследования
    -0.06
    州市
    -0.06
    紀
    -0.06
    oding
    -0.06
     사람
    -0.06
    άλυ
    -0.06
    POSITIVE LOGITS
     facilitate
    0.07
    ates
    0.07
    ATED
    0.06
     AABB
    0.06
    iễn
    0.06
     facilitates
    0.06
     GETGLOBAL
    0.06
    ครงการ
    0.06
     ITE
    0.06
     complexion
    0.06
    Act Density 0.002%

    No Known Activations