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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bigger
    -0.07
     keeps
    -0.06
     decrease
    -0.06
    uktur
    -0.06
    全
    -0.06
    kte
    -0.06
    ites
    -0.06
    ότε
    -0.06
    abilities
    -0.06
     MESSAGE
    -0.06
    POSITIVE LOGITS
    Delete
    0.07
    	board
    0.06
    폭
    0.06
    ा↵
    0.06
     بعضی
    0.06
     담
    0.06
    pytest
    0.06
    Leon
    0.06
     злоч
    0.06
     Львів
    0.06
    Act Density 0.029%

    No Known Activations