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

    Neuronpedia

    INDEX
    Explanations

    machines and equipment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Output
    -0.07
     slot
    -0.07
    454
    -0.06
    ():↵↵
    -0.06
    	ap
    -0.06
    III
    -0.06
    rysler
    -0.06
     Legendary
    -0.06
    obi
    -0.06
     BI
    -0.06
    POSITIVE LOGITS
    μερα
    0.07
     exercising
    0.07
     پیدا
    0.07
    初
    0.06
     гем
    0.06
     javascript
    0.06
    ично
    0.06
     teammates
    0.06
     merak
    0.06
     adım
    0.06
    Act Density 0.022%

    No Known Activations