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

    Neuronpedia

    INDEX
    Explanations

    stopping conditions or base cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    λια
    0.38
    跨境
    0.38
    シャル
    0.37
    newInstance
    0.37
    clientsdetails
    0.37
    قام
    0.36
    バリー
    0.36
    燙
    0.36
     বিশাল
    0.36
    Dropbox
    0.35
    POSITIVE LOGITS
     stop
    1.93
     stopping
    1.92
     Stopping
    1.83
     Stop
    1.80
    停止
    1.80
    Stop
    1.80
    Stopping
    1.80
    stop
    1.79
    stopping
    1.78
     stops
    1.71
    Act Density 0.036%

    No Known Activations