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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     싱글
    -0.06
     Yet
    -0.06
     telling
    -0.06
     overcoming
    -0.06
     ApiController
    -0.06
    —the
    -0.06
     acum
    -0.06
    かった
    -0.06
     remedies
    -0.06
    라이
    -0.06
    POSITIVE LOGITS
    .:.:.:.:
    0.08
     celé
    0.07
     فارس
    0.06
     Colon
    0.06
     společ
    0.06
    =$
    0.06
     دست
    0.06
     म
    0.06
    ΩΣ
    0.06
    oproject
    0.06
    Act Density 0.001%

    No Known Activations