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

    Neuronpedia

    INDEX
    Explanations

    before settling or choosing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indign
    0.37
     riconoscimento
    0.37
     বুদ্ধি
    0.35
     controles
    0.35
     部
    0.34
    认识
    0.34
    什么时候
    0.34
     recognising
    0.33
     riconosc
    0.33
     logical
    0.33
    POSITIVE LOGITS
     selected
    1.91
    selected
    1.79
     Selected
    1.76
    Selected
    1.70
     выбран
    1.68
     chosen
    1.64
     ausgewählt
    1.59
    chosen
    1.58
     seleccionado
    1.58
    Chosen
    1.52
    Act Density 0.010%

    No Known Activations