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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irth
    -0.07
     поб
    -0.06
    �
    -0.06
     ابتدا
    -0.06
    ippo
    -0.06
    اق
    -0.06
     ignition
    -0.06
     schle
    -0.06
     گیر
    -0.06
     миров
    -0.06
    POSITIVE LOGITS
    яет
    0.06
    .hasNext
    0.06
    ************
    0.06
    (savedInstanceState
    0.06
     ██
    0.06
     вак
    0.06
     FBI
    0.06
     відбувається
    0.06
    ้้
    0.06
     Guar
    0.06
    Act Density 0.017%

    No Known Activations