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

    Neuronpedia

    INDEX
    Explanations

    time and date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耂
    0.96
    )^*
    0.83
     glows
    0.81
     treks
    0.81
    StartPreview
    0.81
     mow
    0.80
     boar
    0.80
    zerel
    0.80
    龶
    0.79
    ្ឋ
    0.78
    POSITIVE LOGITS
     unen
    0.68
     رہی
    0.61
    angular
    0.58
     صدر
    0.57
     मिला
    0.57
    カリ
    0.57
     sidang
    0.57
    ப்பாக
    0.56
     IBOutlet
    0.55
    keme
    0.55
    Act Density 0.025%

    No Known Activations