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

    Neuronpedia

    INDEX
    Explanations

    syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reason
    -0.07
    FDA
    -0.07
     flutter
    -0.07
    จะเป
    -0.06
     Gan
    -0.06
     circum
    -0.06
    Reason
    -0.06
     나타
    -0.06
    _MA
    -0.06
     IDirect
    -0.06
    POSITIVE LOGITS
    -------------</
    0.07
     Gün
    0.07
    ydro
    0.07
     shit
    0.06
    すれば
    0.06
    тал
    0.06
    submenu
    0.06
    したら
    0.06
    řízení
    0.06
    !(:
    0.06
    Act Density 0.000%

    No Known Activations