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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HARD
    -0.07
    otional
    -0.06
     pairing
    -0.06
     passports
    -0.06
    ागत
    -0.06
     problematic
    -0.06
    ôm
    -0.06
     paradox
    -0.06
    併
    -0.06
    SELL
    -0.06
    POSITIVE LOGITS
    /*
    0.08
    (Il
    0.08
     миров
    0.07
    /]
    0.07
     удов
    0.07
    |)↵
    0.07
    .retrieve
    0.07
    面
    0.07
     /*
    0.06
    _dma
    0.06
    Act Density 0.012%

    No Known Activations