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

    Neuronpedia

    INDEX
    Explanations

    border entry security and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.80
    Gli
    0.59
    Pri
    0.57
    Sector
    0.57
    ρηση
    0.57
    Mart
    0.56
    urilor
    0.56
    ﻭ
    0.56
    SA
    0.56
    City
    0.55
    POSITIVE LOGITS
     Able
    0.63
     IC
    0.61
     syllables
    0.60
     dolphins
    0.60
     whiskers
    0.59
     caused
    0.58
     IMS
    0.57
     bushels
    0.57
     konstit
    0.57
     lä
    0.57
    Act Density 0.002%

    No Known Activations