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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paddingBottom
    -0.07
     Usa
    -0.07
    0
    -0.07
    ار
    -0.07
    练习
    -0.07
     starts
    -0.07
    =start
    -0.06
     benchmarks
    -0.06
    .'_
    -0.06
     Screens
    -0.06
    POSITIVE LOGITS
     who
    0.12
     qui
    0.08
    who
    0.07
     StreamWriter
    0.07
    qui
    0.07
     fq
    0.06
     Ła
    0.06
     olduğu
    0.06
     miser
    0.06
    érer
    0.06
    Act Density 0.108%

    No Known Activations