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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     작업
    -0.09
     vera
    -0.08
    -ish
    -0.07
     Surgeon
    -0.07
    kol
    -0.07
     тра
    -0.07
    pilot
    -0.07
    ория
    -0.07
    Pilot
    -0.07
     okol
    -0.07
    POSITIVE LOGITS
     মাধ্যম
    0.13
    媒
    0.12
     mediums
    0.12
     माध्यम
    0.11
    途
    0.10
     средство
    0.10
    渠道
    0.10
    方式
    0.10
    机制
    0.10
     الإعلام
    0.10
    Act Density 0.051%

    No Known Activations