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

    Neuronpedia

    INDEX
    Explanations

    causes and effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marc
    -0.07
     devol
    -0.07
    ashes
    -0.07
    astic
    -0.07
    auten
    -0.07
    -0.07
     mereka
    -0.07
     fiance
    -0.07
    Danny
    -0.07
    Marc
    -0.07
    POSITIVE LOGITS
    因素
    0.14
    原因
    0.14
     Ursachen
    0.14
     காரண
    0.13
     Causes
    0.12
     causes
    0.12
     الأسباب
    0.12
     reasons
    0.12
     fatores
    0.12
     Factors
    0.12
    Act Density 0.073%
    No Known Activations