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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Italians
    -0.07
     reconsider
    -0.06
    、「
    -0.06
     ultimate
    -0.06
    แจ
    -0.06
    　　　　
    -0.06
    rtype
    -0.06
     Rand
    -0.06
     tra
    -0.06
    ～～
    -0.06
    POSITIVE LOGITS
    conto
    0.07
     Eagle
    0.07
     Cumberland
    0.06
    Drawable
    0.06
    lok
    0.06
    .backgroundColor
    0.06
    .detail
    0.06
    ght
    0.06
    iosa
    0.06
    Light
    0.06
    Act Density 0.000%

    No Known Activations