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

    Neuronpedia

    INDEX
    Explanations

    newline character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tues
    -0.06
    详
    -0.06
    ург
    -0.06
     Villa
    -0.06
    ertura
    -0.06
    スト
    -0.06
    uctive
    -0.06
    _ts
    -0.06
     Packaging
    -0.06
    陽
    -0.06
    POSITIVE LOGITS
     tượng
    0.07
    	transform
    0.06
    ddit
    0.06
    слід
    0.06
     온
    0.06
     Submit
    0.06
    ậc
    0.06
    ीतर
    0.06
     ecosystems
    0.06
    forgot
    0.06
    Act Density 0.004%

    No Known Activations