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

    Neuronpedia

    INDEX
    Explanations

    places and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     substantiate
    0.64
     moda
    0.60
     characterize
    0.58
    OUBLE
    0.57
    {
    0.57
     financi
    0.56
     mora
    0.55
    чик
    0.55
     চক্র
    0.54
     construe
    0.54
    POSITIVE LOGITS
    یتی
    0.61
     labeled
    0.57
    ißler
    0.55
     Festival
    0.55
    after
    0.54
    pectives
    0.54
    ao
    0.52
    位置
    0.52
     θέση
    0.51
    িয়েত
    0.50
    Act Density 0.018%

    No Known Activations