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

    Neuronpedia

    INDEX
    Explanations

    Algon African converted cleaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Despatx
    0.43
    谯
    0.41
     móc
    0.41
    Museum
    0.40
    博物馆
    0.39
    Vì
    0.38
     그러니까
    0.38
     Fortsch
    0.37
    Ⲃ
    0.36
    ExpireTime
    0.36
    POSITIVE LOGITS
     unge
    0.45
     purposes
    0.43
     Small
    0.40
     dynamics
    0.38
     dynamic
    0.38
     One
    0.38
     AM
    0.38
     un
    0.37
     stuffed
    0.37
     мел
    0.37
    Act Density 0.002%

    No Known Activations