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

    Neuronpedia

    INDEX
    Explanations

    academic research texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wood
    -0.06
     bonding
    -0.06
    izi
    -0.06
    usting
    -0.06
    VA
    -0.06
     Sitting
    -0.06
    лися
    -0.06
    halten
    -0.06
    867
    -0.06
     vap
    -0.06
    POSITIVE LOGITS
    眾
    0.07
     مرب
    0.07
    ="{
    0.06
    -dismissible
    0.06
     ابو
    0.06
     -*-
↵
    0.06
    аков
    0.06
     값
    0.06
    settings
    0.06
    ViewItem
    0.06
    Act Density 0.091%

    No Known Activations