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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Goals
    -0.07
    mıştı
    -0.06
     části
    -0.06
     Feedback
    -0.06
    ænd
    -0.06
     quanh
    -0.06
     OCD
    -0.06
     it
    -0.06
    ladım
    -0.06
     Для
    -0.06
    POSITIVE LOGITS
     examination
    0.08
    628
    0.07
     initialization
    0.07
    _ble
    0.07
    zial
    0.06
     HARD
    0.06
    宣
    0.06
     exhibiting
    0.06
     petitions
    0.06
    晓
    0.06
    Act Density 0.000%

    No Known Activations