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

    Neuronpedia

    INDEX
    Explanations

    being be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ierenden
    -0.08
     destinada
    -0.08
     інш
    -0.08
     stammt
    -0.07
    accent
    -0.07
     Curse
    -0.07
     Curve
    -0.07
     Cur
    -0.07
     sürekli
    -0.07
    selected
    -0.07
    POSITIVE LOGITS
    更加
    0.09
     осторож
    0.09
     proactive
    0.09
     skeptical
    0.08
     opportun
    0.08
     verbose
    0.08
    大胆
    0.08
     timid
    0.08
    严
    0.07
     cautious
    0.07
    Act Density 0.070%

    No Known Activations