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

    Neuronpedia

    INDEX
    Explanations

    Your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    структур
    -0.08
    ワ
    -0.07
     evacuate
    -0.07
    jes
    -0.07
    裔
    -0.07
    鞣
    -0.06
    باحث
    -0.06
    贽
    -0.06
    פוס
    -0.06
    ℱ
    -0.06
    POSITIVE LOGITS
    -moving
    0.07
     Mia
    0.07
    edis
    0.07
    drink
    0.07
     sclerosis
    0.06
    ()],↵
    0.06
     amino
    0.06
    ড
    0.06
    antage
    0.06
    🖖
    0.06
    Act Density 0.005%

    No Known Activations