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

    Neuronpedia

    INDEX
    Explanations

    text formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unt
    -0.07
    [first
    -0.07
     Labor
    -0.07
    _hours
    -0.07
     '.',
    -0.07
    �
    -0.06
    	id
    -0.06
    jaw
    -0.06
    ectors
    -0.06
     Đ
    -0.06
    POSITIVE LOGITS
    achuset
    0.07
     задов
    0.06
    )(*
    0.06
    .latest
    0.06
    .weather
    0.06
    ongoose
    0.06
     traditions
    0.06
    所有
    0.06
     struggles
    0.06
     کاربر
    0.06
    Act Density 0.067%

    No Known Activations