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

    Neuronpedia

    INDEX
    Explanations

    control population growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sharing
    0.52
    Monitoring
    0.51
    Brief
    0.48
    Comparing
    0.48
    Sonic
    0.46
    ก่อน
    0.46
    Round
    0.46
    SUN
    0.46
    COMPAR
    0.45
    ฯ
    0.45
    POSITIVE LOGITS
     kontrol
    0.51
    utt
    0.47
    undaki
    0.46
    attup
    0.45
     haber
    0.45
    indeki
    0.44
    ك
    0.44
    alla
    0.43
     Deut
    0.43
     wasser
    0.43
    Act Density 0.001%

    No Known Activations