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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (object
    -0.07
    _lab
    -0.07
    772
    -0.07
     hiệu
    -0.07
    damage
    -0.06
    _DAC
    -0.06
    _similarity
    -0.06
    oomla
    -0.06
     overlays
    -0.06
     damage
    -0.06
    POSITIVE LOGITS
    ILLS
    0.08
    Dans
    0.07
    ICS
    0.06
     parcels
    0.06
    ΙΑΣ
    0.06
    .WebServlet
    0.06
    эф
    0.06
     Keys
    0.06
    _starts
    0.06
    	dis
    0.06
    Act Density 0.094%

    No Known Activations