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

    Neuronpedia

    INDEX
    Explanations

    investigations/reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     must
    -0.06
    (__
    -0.06
     cerr
    -0.06
    /');↵
    -0.06
    똥
    -0.06
     воздух
    -0.06
     vaccines
    -0.06
     retros
    -0.06
     الص
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    先进
    0.08
    scaling
    0.07
    Supported
    0.07
     Render
    0.07
     Aspen
    0.07
    皞
    0.07
    Offers
    0.07
    ivité
    0.07
     aggregated
    0.07
     enables
    0.07
    Act Density 0.150%

    No Known Activations