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

    Neuronpedia

    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,output
    -0.08
     Recycling
    -0.07
    _death
    -0.07
     sounding
    -0.07
     Problem
    -0.07
     DFS
    -0.07
     trajectories
    -0.06
    published
    -0.06
    Normal
    -0.06
    -des
    -0.06
    POSITIVE LOGITS
     đáng
    0.06
     Scotland
    0.06
    $stmt
    0.06
     Apparel
    0.06
    -gallery
    0.06
     MPG
    0.06
    kraine
    0.06
    (optional
    0.06
     SER
    0.06
     Scottish
    0.06
    Act Density 0.009%

    No Known Activations