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

    Neuronpedia

    INDEX
    Explanations

    uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.51
    kapital
    -0.49
    ">//
    -0.49
     ARIA
    -0.48
     Refugees
    -0.47
     елның
    -0.47
    GEBURTSDATUM
    -0.46
     Piers
    -0.46
     ViewPager
    -0.46
     gemak
    -0.46
    POSITIVE LOGITS
    BufferException
    0.71
    copg
    0.66
    parsedMessage
    0.60
     lenker
    0.56
     contactez
    0.55
    蜒
    0.54
    mability
    0.53
     NSCoder
    0.53
     Nan
    0.52
    Хьажоргаш
    0.52
    Act Density 0.001%

    No Known Activations