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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     root
    3.21
     roots
    3.07
     Root
    3.01
    Root
    2.95
    root
    2.85
     Roots
    2.64
     ROOT
    2.57
    roots
    2.53
    Roots
    2.45
    ROOT
    2.43
    POSITIVE LOGITS
    షణ
    0.65
     teknoloj
    0.64
     লো
    0.60
     DISCLAIMED
    0.59
    edi
    0.59
     Accred
    0.56
     tecnologie
    0.56
     Tecnologia
    0.55
    éis
    0.54
     ধর্ষণ
    0.54
    Act Density 0.025%

    No Known Activations