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

    Neuronpedia

    INDEX
    Explanations

    doors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bus
    -0.06
     बह
    -0.06
    _locale
    -0.06
    oooooooo
    -0.06
    urgence
    -0.06
    _Mod
    -0.06
     hizmet
    -0.06
    little
    -0.06
    озі
    -0.06
    ject
    -0.06
    POSITIVE LOGITS
    衣
    0.06
    нина
    0.06
    균
    0.06
     （
    0.06
     верес
    0.06
     sdf
    0.06
    assignments
    0.06
    .pkg
    0.06
    /start
    0.06
     گزارش
    0.06
    Act Density 0.005%

    No Known Activations