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

    Neuronpedia

    INDEX
    Explanations

    Companies, brands, and designations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хо
    1.17
    t
    1.16
    NET
    1.07
    ત
    1.07
    عکس
    1.01
    ver
    1.00
    $,
    0.99
    ]【
    0.99
    Serialize
    0.98
    О
    0.98
    POSITIVE LOGITS
    ാ
    1.57
    ীবন
    1.39
    er
    1.33
     watchful
    1.28
     didn
    1.26
    ER
    1.25
    をと
    1.25
     indeterm
    1.23
     पिछली
    1.23
     doesn
    1.23
    Act Density 0.048%

    No Known Activations