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

    Neuronpedia

    INDEX
    Explanations

    fixed gaze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flea
    -0.07
    idor
    -0.06
    -ins
    -0.06
     orbits
    -0.06
    修改
    -0.06
     Afro
    -0.06
    curr
    -0.06
    xiety
    -0.06
    illez
    -0.06
     sims
    -0.06
    POSITIVE LOGITS
    .CODE
    0.07
    ามารถ
    0.06
     loyal
    0.06
     závis
    0.06
    ัญญ
    0.06
    .parentNode
    0.06
    定
    0.06
     اینکه
    0.06
    978
    0.06
     snatch
    0.06
    Act Density 0.013%

    No Known Activations