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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     высокой
    -0.07
    बर
    -0.07
    parseInt
    -0.07
    真的
    -0.06
     Hindered
    -0.06
     ένα
    -0.06
    _my
    -0.06
    /results
    -0.06
    indrome
    -0.06
    Frequency
    -0.06
    POSITIVE LOGITS
     раст
    0.07
    ุบ
    0.06
    �
    0.06
    )]↵
    0.06
    _nom
    0.06
    :
    0.06
     :
    0.06
    )↵
    0.06
     —
    0.06
    ">↵
    0.06
    Act Density 0.006%

    No Known Activations