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

    Neuronpedia

    INDEX
    Explanations

    "Loki" and "Satoshi" names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'ag
    -0.08
     inlet
    -0.08
    ಕ್ಷಣ
    -0.07
     expend
    -0.07
     והש
    -0.07
    boden
    -0.07
     segmented
    -0.07
     pollut
    -0.07
    क्षक
    -0.07
    itivity
    -0.07
    POSITIVE LOGITS
     ഒരുക്ക
    0.08
     తయ
    0.08
     നിർമ്മ
    0.08
    Deliver
    0.08
    Rollback
    0.07
     izdel
    0.07
     Procur
    0.07
     jäl
    0.07
     textbooks
    0.07
    فيات
    0.07
    Act Density 0.001%

    No Known Activations