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

    Neuronpedia

    INDEX
    Explanations

    **:**, ignore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    对待
    0.45
     augustus
    0.45
    ainak
    0.44
    Tabpage
    0.44
    ivé
    0.44
     μεγαλ
    0.43
     تھے
    0.43
     zostało
    0.43
     estavam
    0.42
     منظور
    0.42
    POSITIVE LOGITS
    akrishnan
    0.47
    なぜ
    0.46
     VPN
    0.43
    ញ្
    0.42
    تا
    0.41
     bumpy
    0.41
    煥
    0.40
     bosons
    0.39
    ल
    0.39
    倫
    0.39
    Act Density 0.003%

    No Known Activations