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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	TR
    -0.07
    .Lookup
    -0.07
    ssel
    -0.07
     holy
    -0.06
    -ver
    -0.06
     Hague
    -0.06
    _Flag
    -0.06
     memoir
    -0.06
    -fix
    -0.06
    irable
    -0.06
    POSITIVE LOGITS
    abilities
    0.06
     української
    0.06
     تغ
    0.06
    .ex
    0.06
    cpt
    0.06
    methodName
    0.06
    /forms
    0.06
     enquiries
    0.06
     responsive
    0.06
    бот
    0.06
    Act Density 0.017%

    No Known Activations