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

    Neuronpedia

    INDEX
    Explanations

    computer formatting/clearing data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '):
    -0.07
    جاد
    -0.07
     sample
    -0.06
    _trap
    -0.06
     shadow
    -0.06
    Withdraw
    -0.06
    nia
    -0.06
     shadows
    -0.06
    pin
    -0.06
     Warp
    -0.06
    POSITIVE LOGITS
     ppl
    0.07
     iht
    0.07
    ีป
    0.07
     gallon
    0.06
    odic
    0.06
    ість
    0.06
     sıcak
    0.06
     =$
    0.06
    台灣
    0.06
    �
    0.06
    Act Density 0.056%

    No Known Activations