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

    Neuronpedia

    INDEX
    Explanations

    subtractions or deductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đương
    -0.07
    �
    -0.07
     застав
    -0.06
    �
    -0.06
     경북
    -0.06
    ヴァ
    -0.06
     décou
    -0.06
    単
    -0.06
    �
    -0.06
     qa
    -0.06
    POSITIVE LOGITS
     #↵
    0.08
    appable
    0.07
     WORLD
    0.07
    #↵
    0.06
    /></
    0.06
    /check
    0.06
    roleId
    0.06
     IonicPage
    0.06
     eğ
    0.06
    mares
    0.06
    Act Density 0.060%

    No Known Activations