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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GENER
    -0.07
     Voltage
    -0.06
     departed
    -0.06
     lengths
    -0.06
     apache
    -0.06
     integrated
    -0.06
     simplified
    -0.06
    Layers
    -0.06
     Info
    -0.06
     Mode
    -0.06
    POSITIVE LOGITS
    Ѓ
    0.08
     replen
    0.07
    _WRONG
    0.07
     apiUrl
    0.07
    _quota
    0.07
    áy
    0.07
     سرد
    0.07
    _sleep
    0.06
     QTimer
    0.06
     ป
    0.06
    Act Density 0.008%

    No Known Activations