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

    Neuronpedia

    INDEX
    Explanations

    foster, adopted, host family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onsite
    0.41
     flying
    0.41
     Immortal
    0.41
     flights
    0.40
     progeny
    0.40
     flight
    0.40
    空中
    0.39
    تاجها
    0.38
     tonos
    0.36
     antisocial
    0.36
    POSITIVE LOGITS
     adoptive
    0.80
     foster
    0.73
    Foster
    0.66
     adopters
    0.60
    Adopt
    0.60
    adopted
    0.59
     adopted
    0.59
    家庭
    0.59
     fostered
    0.59
     Foster
    0.57
    Act Density 0.026%

    No Known Activations