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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clare
    -0.07
     rumours
    -0.07
    ꒫
    -0.07
    $args
    -0.07
    加拿大
    -0.07
     (!
    -0.07
     factions
    -0.07
     therapists
    -0.07
     помог
    -0.07
    (storage
    -0.06
    POSITIVE LOGITS
    eting
    0.07
     Xu
    0.07
     Kane
    0.07
    -gen
    0.07
    ฟา
    0.07
    发电
    0.07
     Motorola
    0.06
    发射
    0.06
     Carrier
    0.06
    	en
    0.06
    Act Density 0.237%

    No Known Activations