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

    Neuronpedia

    INDEX
    Explanations

    Code/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    児
    -0.07
    _LIGHT
    -0.06
    ニュ
    -0.06
    ναν
    -0.06
    cedures
    -0.06
    DR
    -0.06
     HDF
    -0.06
    balance
    -0.06
    Hp
    -0.06
     Houses
    -0.06
    POSITIVE LOGITS
    δες
    0.07
     ragazza
    0.07
     inner
    0.07
     raided
    0.07
     Kons
    0.06
     Terra
    0.06
     Tou
    0.06
     Bi
    0.06
     Moral
    0.06
     第三
    0.06
    Act Density 0.001%

    No Known Activations