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

    Neuronpedia

    INDEX
    Explanations

    Marine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foo
    -0.07
    乐
    -0.06
     अख
    -0.06
     Wit
    -0.06
    樂
    -0.06
     فیلم
    -0.06
     holiday
    -0.06
    roulette
    -0.06
     restart
    -0.06
    pytest
    -0.06
    POSITIVE LOGITS
     Marine
    0.09
     कन
    0.08
     marine
    0.07
    _SAN
    0.07
     sermon
    0.07
    ereço
    0.07
    water
    0.07
    ma
    0.07
     Yankees
    0.07
     brass
    0.07
    Act Density 0.005%

    No Known Activations