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

    Neuronpedia

    INDEX
    Explanations

    one or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秏
    0.43
     SMITH
    0.40
    /}
    0.40
    ambers
    0.38
    梼
    0.38
    Idaho
    0.38
     شفاف
    0.38
    acotta
    0.37
     viscose
    0.37
    फोटो
    0.36
    POSITIVE LOGITS
     namelijk
    0.47
     Bj
    0.42
     Agust
    0.42
     ovvero
    0.41
     Ful
    0.39
     moreover
    0.39
     Maven
    0.39
     Moreover
    0.38
     Zuge
    0.38
     Gw
    0.37
    Act Density 0.001%

    No Known Activations