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

    Neuronpedia

    INDEX
    Explanations

    Users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Had
    -0.07
    spots
    -0.07
    を取り
    -0.07
    rzą
    -0.07
    แห
    -0.06
    .Op
    -0.06
     yö
    -0.06
     �
    -0.06
    start
    -0.06
    .figure
    -0.06
    POSITIVE LOGITS
    韩国
    0.07
     zwar
    0.07
    ies
    0.07
    بيعي
    0.07
    ✶
    0.07
    ᵭ
    0.07
    =result
    0.07
    le
    0.06
    🥦
    0.06
    賴
    0.06
    Act Density 0.001%

    No Known Activations