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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сю
    -0.07
    馬
    -0.06
    �y
    -0.06
    plit
    -0.06
     RV
    -0.06
     празд
    -0.06
    �i
    -0.06
    vědom
    -0.06
    neas
    -0.06
    -AA
    -0.06
    POSITIVE LOGITS
    (engine
    0.07
     बत
    0.06
     eyewitness
    0.06
     ViewController
    0.06
    _payload
    0.06
     wishes
    0.06
     launcher
    0.06
    Interpreter
    0.06
    ))))↵
    0.06
    ']=
    0.06
    Act Density 0.002%

    No Known Activations