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

    Neuronpedia

    INDEX
    Explanations

    BI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mara
    -0.08
     IST
    -0.07
     LOCAL
    -0.07
    oz
    -0.07
     tra
    -0.07
     responds
    -0.07
    (term
    -0.06
    .R
    -0.06
    を使
    -0.06
    Wo
    -0.06
    POSITIVE LOGITS
    BI
    0.08
     деп
    0.07
     Opport
    0.07
    ᑭ
    0.07
    _trajectory
    0.07
    expectException
    0.07
    postId
    0.06
    (productId
    0.06
    펠
    0.06
    蜣
    0.06
    Act Density 0.040%

    No Known Activations