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

    Neuronpedia

    INDEX
    Explanations

    this way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crum
    0.42
     Arten
    0.40
     recol
    0.39
     effic
    0.38
     vat
    0.38
     specific
    0.38
     generic
    0.38
    iggers
    0.38
     postpaid
    0.38
     imediat
    0.37
    POSITIVE LOGITS
     dabb
    0.69
     dab
    0.62
     amateur
    0.58
     музыкан
    0.57
     겸
    0.55
     foray
    0.50
     Amateur
    0.49
     সাহিত্য
    0.47
     amateurs
    0.45
    亲自
    0.45
    Act Density 0.105%

    No Known Activations