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

    Neuronpedia

    INDEX
    Explanations

    Resource management code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PROD
    -0.06
    彩
    -0.06
     murdering
    -0.06
    .sparse
    -0.06
    .score
    -0.06
     شناخته
    -0.06
    �
    -0.06
    imitives
    -0.06
    Mount
    -0.06
    ของค
    -0.06
    POSITIVE LOGITS
     général
    0.07
    Conv
    0.06
     ammon
    0.06
     пре
    0.06
     Collection
    0.06
     Amelia
    0.06
    -plan
    0.06
     özelliği
    0.06
     Exact
    0.06
    	es
    0.06
    Act Density 0.008%

    No Known Activations