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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    drops
    -0.06
    arrings
    -0.06
     uçak
    -0.06
    ,nil
    -0.06
     почему
    -0.06
     солн
    -0.06
    ウォ
    -0.06
    옥
    -0.06
    _NOTIFY
    -0.06
    POSITIVE LOGITS
     "-",
    0.07
    _have
    0.07
     vibrant
    0.06
    	ar
    0.06
     primarily
    0.06
     $(
    0.06
     Evalu
    0.06
    タン
    0.06
    adopt
    0.06
    {(
    0.06
    Act Density 0.004%

    No Known Activations