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

    Neuronpedia

    INDEX
    Explanations

    update or edit operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adiabatically
    0.46
     pine
    0.42
     potenz
    0.40
     poles
    0.40
     آ
    0.39
     sorption
    0.39
     monasteries
    0.39
     refroidissement
    0.39
     unités
    0.39
     fünf
    0.38
    POSITIVE LOGITS
    Update
    0.92
    update
    0.91
    修改
    0.88
     updating
    0.86
     UPDATE
    0.85
    更新
    0.84
     Updating
    0.83
     update
    0.83
     Update
    0.83
    UPDATE
    0.80
    Act Density 0.146%

    No Known Activations