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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pvt
    -0.06
    analy
    -0.06
     vẫn
    -0.06
     контак
    -0.06
    ाइ
    -0.06
     Ris
    -0.05
     Bowen
    -0.05
     apl
    -0.05
    .account
    -0.05
     Firearms
    -0.05
    POSITIVE LOGITS
    xc
    0.07
     txt
    0.07
    _HELP
    0.07
    gay
    0.07
     avg
    0.07
    .doc
    0.07
    MMM
    0.07
     wilderness
    0.06
     reclaimed
    0.06
     FIL
    0.06
    Act Density 0.002%

    No Known Activations