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

    Neuronpedia

    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (todo
    -0.07
    >O
    -0.07
    .gold
    -0.07
    .getNum
    -0.07
     criticised
    -0.07
    🎬
    -0.07
    劼
    -0.06
    三年级
    -0.06
    >d
    -0.06
    شه
    -0.06
    POSITIVE LOGITS
    lagen
    0.07
     Banner
    0.07
    䋌
    0.07
    ߪ
    0.07
     '?'
    0.07
    -space
    0.06
     haben
    0.06
     SCREEN
    0.06
     conservative
    0.06
     Special
    0.06
    Act Density 0.010%

    No Known Activations