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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pile
    -0.06
    Coder
    -0.06
     sections
    -0.06
     divisor
    -0.06
     violates
    -0.06
     станов
    -0.06
     έναν
    -0.06
    ーデ
    -0.06
     networking
    -0.06
     spawn
    -0.06
    POSITIVE LOGITS
    리
    0.07
    ,[],
    0.06
    xFFFFFF
    0.06
    ValueType
    0.06
    ()',
    0.06
    Nike
    0.06
    ΑΝΤ
    0.06
     浙江
    0.06
    跑
    0.06
    -Compatible
    0.06
    Act Density 0.024%

    No Known Activations