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
     PURPOSE
    -0.07
    �
    -0.07
     ocean
    -0.07
    ز
    -0.07
     theme
    -0.07
    han
    -0.07
     ie
    -0.06
     Diary
    -0.06
     dau
    -0.06
     Vý
    -0.06
    POSITIVE LOGITS
    ifference
    0.07
    catid
    0.06
    urum
    0.06
    eeper
    0.06
     Governance
    0.06
     expo
    0.06
    //================================================================
    0.05
    arduino
    0.05
    anger
    0.05
    ूस
    0.05
    Act Density 0.306%

    No Known Activations