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

    Neuronpedia

    INDEX
    Explanations

    videos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edmund
    -0.07
    tual
    -0.06
    ewan
    -0.06
    .DataGridViewColumn
    -0.06
    .av
    -0.06
    _tgt
    -0.06
    خرید
    -0.06
     Dolphin
    -0.06
     dom
    -0.06
     dziewcz
    -0.06
    POSITIVE LOGITS
     합
    0.07
     chỉnh
    0.07
    _upd
    0.07
     indiscrim
    0.07
     pillar
    0.06
    ….↵↵
    0.06
     prescribe
    0.06
    braco
    0.06
    .FileName
    0.06
    ラク
    0.06
    Act Density 0.000%

    No Known Activations