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

    Neuronpedia

    INDEX
    Explanations

    modelrelated to keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verhindern
    0.84
     ترلاسه
    0.79
     emerging
    0.78
     emerged
    0.77
     verfol
    0.75
     betont
    0.74
     обрабаты
    0.74
     छीन
    0.73
    잊
    0.72
     shaking
    0.72
    POSITIVE LOGITS
     посвя
    0.75
    ட்ப
    0.68
    寄
    0.66
     ಸಂಬಂಧ
    0.66
     വേണ്ടി
    0.65
     dédi
    0.64
    Wasser
    0.63
     సంబంధించిన
    0.60
    AndKeys
    0.60
     Keys
    0.59
    Act Density 0.093%

    No Known Activations