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

    Neuronpedia

    INDEX
    Explanations

    compatible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excursion
    -0.07
    خرو
    -0.07
    (nodes
    -0.07
    bff
    -0.06
    探究
    -0.06
    _offer
    -0.06
     escap
    -0.06
    各有
    -0.06
     사건
    -0.06
    /navigation
    -0.06
    POSITIVE LOGITS
    朕
    0.08
     Gotham
    0.07
    unes
    0.07
    ReturnType
    0.07
     pictureBox
    0.07
     infantry
    0.07
     balanced
    0.06
    Dice
    0.06
    PGA
    0.06
     souha
    0.06
    Act Density 0.008%

    No Known Activations