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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quer
    -0.07
     Cooke
    -0.06
    .fixture
    -0.06
    .ol
    -0.06
    으
    -0.06
    缓
    -0.06
     soit
    -0.06
    ватися
    -0.06
    icol
    -0.06
     è
    -0.06
    POSITIVE LOGITS
    _num
    0.07
    ียง
    0.06
    kaç
    0.06
     gallery
    0.06
     yüzden
    0.06
    _down
    0.06
    installer
    0.06
     Tyler
    0.06
     tamil
    0.06
    	admin
    0.06
    Act Density 0.009%

    No Known Activations