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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nyder
    -0.07
    _S
    -0.06
     distracted
    -0.06
    oolStrip
    -0.06
    英国
    -0.06
    -driving
    -0.06
    乾
    -0.06
     гір
    -0.06
    (loop
    -0.06
    สด
    -0.06
    POSITIVE LOGITS
     จำ
    0.07
     addon
    0.07
    -os
    0.06
     зак
    0.06
    ござ
    0.06
    回到
    0.06
    =============↵
    0.06
    EventData
    0.05
     Brill
    0.05
     duvar
    0.05
    Act Density 0.011%

    No Known Activations