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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بأ
    -0.07
    onnement
    -0.07
    آمد
    -0.07
    ाएग
    -0.07
     curs
    -0.06
    νά
    -0.06
     meld
    -0.06
     jiných
    -0.06
     desar
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     중국
    0.07
    -\
    0.07
    'https
    0.07
    (ss
    0.07
    /Object
    0.07
    (SE
    0.06
     justice
    0.06
     ones
    0.06
     refill
    0.06
    REMOTE
    0.06
    Act Density 0.000%

    No Known Activations