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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phổ
    0.42
     ወይም
    0.41
     அல்லது
    0.39
     класси
    0.39
     classico
    0.39
     بر
    0.39
    经典
    0.38
     androgen
    0.37
     ошибки
    0.36
     மொழ
    0.36
    POSITIVE LOGITS
     Courthouse
    0.39
     이날
    0.39
    esterday
    0.38
     Saturday
    0.37
     bevor
    0.37
     yesterday
    0.36
     उक्त
    0.36
     அந்
    0.36
     Yesterday
    0.35
     Whom
    0.34
    Act Density 0.027%

    No Known Activations