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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dramatic
    -0.07
     sixth
    -0.07
    �
    -0.07
     Kub
    -0.07
    ’deki
    -0.06
    \Query
    -0.06
     Remain
    -0.06
     Kay
    -0.06
     ниж
    -0.06
    ###
    -0.06
    POSITIVE LOGITS
    100
    0.16
    101
    0.07
    (resultSet
    0.06
    辦
    0.06
    _MATH
    0.06
    척
    0.06
    会
    0.06
     ALS
    0.06
    hardt
    0.06
    (person
    0.06
    Act Density 0.024%

    No Known Activations