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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーション
    -0.07
     pineapple
    -0.07
     radioButton
    -0.07
    坂
    -0.07
     Patriot
    -0.06
    _instr
    -0.06
    Licensed
    -0.06
     Wheel
    -0.06
    기의
    -0.06
     ταιν
    -0.06
    POSITIVE LOGITS
     clinicians
    0.06
    oze
    0.06
    ations
    0.06
     Stability
    0.06
    πον
    0.06
    ività
    0.06
    hunter
    0.06
    -workers
    0.06
    -aut
    0.06
     특별
    0.05
    Act Density 0.002%

    No Known Activations