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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הד
    -0.07
    REEN
    -0.07
    鸳
    -0.06
     Cannes
    -0.06
    [][
    -0.06
    Cs
    -0.06
     пов
    -0.06
     concat
    -0.06
     Beau
    -0.06
     connected
    -0.06
    POSITIVE LOGITS
     lettre
    0.07
     Month
    0.07
     качество
    0.07
    _corpus
    0.07
    éparation
    0.06
    archical
    0.06
    _charset
    0.06
     JT
    0.06
     prohibiting
    0.06
     hakkında
    0.06
    Act Density 0.049%

    No Known Activations