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
    UILTIN
    -0.07
     cabo
    -0.07
     rehearsal
    -0.07
    реть
    -0.07
     得
    -0.07
    غير
    -0.07
    maal
    -0.06
    astered
    -0.06
     край
    -0.06
    .MSG
    -0.06
    POSITIVE LOGITS
    :_
    0.08
    archives
    0.07
    instant
    0.07
     zlib
    0.06
    Receipt
    0.06
     IW
    0.06
    <c
    0.06
    _
    0.06
     accused
    0.06
     المملكة
    0.06
    Act Density 0.005%

    No Known Activations