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

    Neuronpedia

    INDEX
    Explanations

    Update

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只不过是
    -0.07
    	ms
    -0.07
    ถน
    -0.07
    WB
    -0.07
    ADATA
    -0.07
    hoe
    -0.07
     enticing
    -0.07
    明年
    -0.07
    money
    -0.07
     longstanding
    -0.07
    POSITIVE LOGITS
    ביר
    0.07
    rray
    0.07
    Seller
    0.07
    Authors
    0.07
     IonicModule
    0.06
    噔
    0.06
     Yours
    0.06
     pix
    0.06
    ainers
    0.06
     Summary
    0.06
    Act Density 0.012%

    No Known Activations