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

    Neuronpedia

    INDEX
    Explanations

    numerical values and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     institutional
    0.48
     legitim
    0.46
     Institutional
    0.45
    Institutional
    0.43
    institutional
    0.43
     Pim
    0.43
     Stef
    0.42
     sanctioned
    0.41
     authorised
    0.41
     legalized
    0.40
    POSITIVE LOGITS
    scriptsize
    0.39
    navigations
    0.39
    どれ
    0.38
     Navigation
    0.37
     table
    0.37
    slots
    0.37
     divided
    0.37
    Old
    0.37
     Moved
    0.36
     Фер
    0.36
    Act Density 0.000%

    No Known Activations