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

    Neuronpedia

    INDEX
    Explanations

    promotional giveaways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iteur
    -0.07
    온
    -0.07
    .YELLOW
    -0.07
    _ter
    -0.06
     Clinical
    -0.06
     dou
    -0.06
    olecular
    -0.06
    нг
    -0.06
    .Global
    -0.06
    .gz
    -0.06
    POSITIVE LOGITS
    ITO
    0.07
    ｀
    0.07
    승
    0.06
     PY
    0.06
     À
    0.06
    _appro
    0.06
     stri
    0.06
    DIFF
    0.06
    Ren
    0.06
    onation
    0.06
    Act Density 0.031%

    No Known Activations