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

    Neuronpedia

    INDEX
    Explanations

    ingestion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /animations
    -0.07
     Curt
    -0.07
     Dodd
    -0.07
    xb
    -0.07
    인터
    -0.07
     butt
    -0.06
    榄
    -0.06
                                        ↵
    -0.06
    叟
    -0.06
     Arbitrary
    -0.06
    POSITIVE LOGITS
     James
    0.08
    ㏈
    0.07
    拜师学艺
    0.06
     Datos
    0.06
    лас
    0.06
     propio
    0.06
    .tree
    0.06
    愤怒
    0.06
     severely
    0.06
    astic
    0.06
    Act Density 0.013%

    No Known Activations