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

    Neuronpedia

    INDEX
    Explanations

    shapes and sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exemplo
    -0.07
     Pork
    -0.07
    	Add
    -0.07
    ちゃん
    -0.07
    ládá
    -0.06
    푸
    -0.06
     Cann
    -0.06
    Vertex
    -0.06
    (EC
    -0.06
    “How
    -0.06
    POSITIVE LOGITS
     hosting
    0.06
     catal
    0.06
     afect
    0.06
     сбор
    0.06
     αυ
    0.06
    irmed
    0.06
     velocidad
    0.06
    صد
    0.06
     demolition
    0.05
    ?,
    0.05
    Act Density 0.051%

    No Known Activations