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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     folders
    -0.07
     uzak
    -0.07
     дві
    -0.07
     theory
    -0.06
    empre
    -0.06
     Mö
    -0.06
    (pk
    -0.06
     sudo
    -0.06
     HTC
    -0.06
    quality
    -0.06
    POSITIVE LOGITS
     wearable
    0.07
    -----------*/↵
    0.06
     Mighty
    0.06
     نادي
    0.06
    ，更
    0.06
     meticulously
    0.06
    大き
    0.06
     aşam
    0.06
     aller
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations