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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خب
    -0.08
    éder
    -0.08
    ousands
    -0.07
     Kudos
    -0.07
    067
    -0.07
     снова
    -0.07
     takže
    -0.07
     चीज
    -0.07
    fallback
    -0.07
     ETA
    -0.07
    POSITIVE LOGITS
     studied
    0.15
     investigated
    0.15
     अध्ययन
    0.13
     untersucht
    0.13
     investigate
    0.13
     investigates
    0.13
     investigating
    0.12
     তদন্ত
    0.12
     studying
    0.12
     অধ্য
    0.12
    Act Density 0.127%

    No Known Activations