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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restaur
    -0.08
    endors
    -0.07
    Thread
    -0.06
    .net
    -0.06
    crap
    -0.06
     Powered
    -0.06
     SINGLE
    -0.06
    Steven
    -0.06
     Single
    -0.06
    $a
    -0.06
    POSITIVE LOGITS
     partnerships
    0.07
    .Css
    0.07
     cong
    0.07
    っち
    0.06
    δέ
    0.06
    _ENCOD
    0.06
     продукції
    0.06
    简
    0.06
    Mod
    0.06
     Tiếng
    0.06
    Act Density 0.001%

    No Known Activations