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

    Neuronpedia

    INDEX
    Explanations

    age ranges and specific ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    learned
    0.40
    environmental
    0.39
     merkezi
    0.38
    hele
    0.38
    heus
    0.38
    ard
    0.38
    ut
    0.37
    seventh
    0.37
    ätt
    0.37
    legraf
    0.37
    POSITIVE LOGITS
     ages
    0.58
     tuổi
    0.55
     Ages
    0.54
    年齢
    0.53
     возраст
    0.53
     yaş
    0.52
     age
    0.51
     edad
    0.51
     العمر
    0.50
     edades
    0.49
    Act Density 0.001%

    No Known Activations