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

    Neuronpedia

    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iyeti
    -0.09
    Card
    -0.07
     mois
    -0.07
     území
    -0.07
     není
    -0.07
    -paid
    -0.06
    'être
    -0.06
     diese
    -0.06
     fais
    -0.06
    ordinal
    -0.06
    POSITIVE LOGITS
     Hastings
    0.07
    /controller
    0.06
    此
    0.06
     خانه
    0.06
    为
    0.06
    _expect
    0.06
     измер
    0.06
    itect
    0.06
     Unified
    0.06
    切り
    0.06
    Act Density 0.011%

    No Known Activations