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

    Neuronpedia

    INDEX
    Explanations

    Gets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iplina
    -0.07
    ::__
    -0.07
    apur
    -0.06
    ।
    -0.06
    _return
    -0.06
    忍
    -0.06
    {name
    -0.06
     ashes
    -0.06
    (vehicle
    -0.06
    Spacing
    -0.06
    POSITIVE LOGITS
     cocktails
    0.07
    。お
    0.07
    quent
    0.06
     hackers
    0.06
     cập
    0.06
    hardt
    0.06
     Cardinal
    0.06
    iming
    0.06
     Checks
    0.06
    startIndex
    0.06
    Act Density 0.003%

    No Known Activations