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
    wdx
    -0.06
    _P
    -0.06
     Panama
    -0.06
    _tel
    -0.06
    _up
    -0.06
    	R
    -0.06
     Davies
    -0.06
    kest
    -0.06
    iky
    -0.06
    验证
    -0.06
    POSITIVE LOGITS
    <()>
    0.07
     사람들이
    0.07
     هستند
    0.07
    られた
    0.06
    .Warn
    0.06
    aliyet
    0.06
     вели
    0.06
     결혼
    0.06
    campaign
    0.06
    ЙЙ
    0.06
    Act Density 0.001%

    No Known Activations