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

    Neuronpedia

    INDEX
    Explanations

    heritage, monuments, historical sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gesellschaft
    0.49
    ocial
    0.48
    y
    0.48
     soziale
    0.46
     verksam
    0.45
    メリカ
    0.44
     harming
    0.44
    pine
    0.44
     llc
    0.43
    social
    0.42
    POSITIVE LOGITS
     Monuments
    0.47
     daje
    0.46
     Patrim
    0.45
     montagnes
    0.44
     Gap
    0.44
    อะไร
    0.44
     masterpieces
    0.43
    Время
    0.43
     montre
    0.43
     montrer
    0.42
    Act Density 0.029%

    No Known Activations