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

    Neuronpedia

    INDEX
    Explanations

    conversational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bin
    -0.07
    mentation
    -0.07
    ax
    -0.07
    abela
    -0.07
     student
    -0.07
    訂
    -0.07
    gl
    -0.06
    continue
    -0.06
    app
    -0.06
     swimming
    -0.06
    POSITIVE LOGITS
    ジオ
    0.07
    cantidad
    0.06
     moderated
    0.06
     یوتی
    0.06
     aVar
    0.06
    .activities
    0.06
    .spec
    0.06
     opioids
    0.06
    .cz
    0.06
    価格
    0.05
    Act Density 0.088%

    No Known Activations