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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Europe
    -0.07
     pán
    -0.06
    _Two
    -0.06
     IV
    -0.06
     будущ
    -0.06
     Visitors
    -0.06
     informant
    -0.06
     Shack
    -0.06
     Thorn
    -0.06
    [];↵↵
    -0.06
    POSITIVE LOGITS
     msgs
    0.07
     lifting
    0.07
     сл
    0.06
     bitte
    0.06
     всей
    0.06
    .AutoSize
    0.06
    mina
    0.06
     yan
    0.06
     penetr
    0.06
    utf
    0.06
    Act Density 0.038%

    No Known Activations