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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Folder
    0.46
     B
    0.43
     carpeta
    0.42
     D
    0.40
     †
    0.38
     K
    0.38
    Hemos
    0.38
     getText
    0.37
     Lauder
    0.37
     ?",
    0.37
    POSITIVE LOGITS
    IMATE
    0.40
    केशन
    0.39
    IPSET
    0.38
    ГЭ
    0.38
    loose
    0.38
     થશે
    0.38
    araoh
    0.37
     একে
    0.36
    فرض
    0.36
    üedad
    0.36
    Act Density 0.001%

    No Known Activations