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

    Neuronpedia

    INDEX
    Explanations

    inhabit, work, operate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exemplaires
    0.48
     versions
    0.47
     высокой
    0.46
    主要
    0.45
     combos
    0.43
     details
    0.42
     പ്രത്യേ
    0.40
    你可以
    0.40
     grabbing
    0.39
     grabbed
    0.39
    POSITIVE LOGITS
     inhabit
    0.48
     inhabited
    0.46
     rodean
    0.46
     surrounded
    0.46
     inhab
    0.45
     engender
    0.45
     ymp
    0.44
     entour
    0.43
     entrusted
    0.43
    nsec
    0.43
    Act Density 0.011%

    No Known Activations