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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eq
    -0.07
    ，再
    -0.07
    พาะ
    -0.06
    kommen
    -0.06
    halt
    -0.06
    duplicate
    -0.06
    Okay
    -0.06
    contact
    -0.06
    _centers
    -0.06
     Tut
    -0.06
    POSITIVE LOGITS
     unut
    0.08
     мит
    0.07
    warts
    0.07
     φορ
    0.06
     warmth
    0.06
    чер
    0.06
     assort
    0.06
    otion
    0.06
    �
    0.06
    ΑΤ
    0.06
    Act Density 0.131%

    No Known Activations