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

    Neuronpedia

    INDEX
    Explanations

    religious contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ignore
    -0.07
     first
    -0.07
    、三
    -0.07
     insist
    -0.06
     Vintage
    -0.06
     bottoms
    -0.06
    +↵
    -0.06
     named
    -0.06
     Division
    -0.06
     axial
    -0.06
    POSITIVE LOGITS
    pet
    0.08
    acas
    0.07
    �
    0.06
    -Nov
    0.06
    取得
    0.06
     hast
    0.06
     كثير
    0.06
     Afterwards
    0.06
    .innerHTML
    0.06
    ีด
    0.06
    Act Density 0.027%

    No Known Activations