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

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saint
    -0.07
    France
    -0.07
     uncomfortable
    -0.07
    -pressure
    -0.06
     kommer
    -0.06
     fearless
    -0.06
     KH
    -0.06
    有一
    -0.06
     lai
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    �
    0.08
    //{↵
    0.06
     =>{↵
    0.06
     znění
    0.06
    يرة
    0.06
    :'',
    0.06
    uez
    0.06
    ΩΣ
    0.06
    Ace
    0.06
    --){↵
    0.06
    Act Density 0.040%

    No Known Activations