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

    Neuronpedia

    INDEX
    Explanations

    business, index, api, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ómago
    0.59
    ܤ
    0.57
    érons
    0.53
    ILabel
    0.52
    vgili
    0.52
    NoStop
    0.52
     Undoubtedly
    0.52
    म्प्ट
    0.52
    ﮈ
    0.52
    לא
    0.51
    POSITIVE LOGITS
     well
    0.60
     pickles
    0.54
     zip
    0.50
     sushi
    0.49
     smug
    0.49
     frig
    0.49
     poche
    0.49
     infrastructure
    0.48
     stuff
    0.48
     fracking
    0.47
    Act Density 0.141%

    No Known Activations