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

    Neuronpedia

    INDEX
    Explanations

    theros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Imagine
    -0.07
     scrapy
    -0.07
     Imagine
    -0.07
    $db
    -0.07
    cé
    -0.07
    _ray
    -0.06
    ases
    -0.06
     Efficient
    -0.06
     Sing
    -0.06
    aud
    -0.06
    POSITIVE LOGITS
    theros
    0.16
    맥
    0.07
     explosives
    0.07
    -des
    0.06
    phis
    0.06
     SHR
    0.06
    (regex
    0.06
     beneath
    0.06
    mAh
    0.06
     fatally
    0.06
    Act Density 0.001%

    No Known Activations