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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洲
    -0.07
     گاه
    -0.07
    13
    -0.06
     накоп
    -0.06
    عنوان
    -0.06
    „P
    -0.06
     AccessToken
    -0.06
    week
    -0.06
     setSupportActionBar
    -0.06
     واس
    -0.06
    POSITIVE LOGITS
    ERC
    0.07
    grep
    0.07
     convincing
    0.07
    üyle
    0.06
    われ
    0.06
    ucene
    0.06
     Simple
    0.06
     diret
    0.06
     violence
    0.06
    useState
    0.06
    Act Density 0.010%

    No Known Activations