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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assumption
    -0.08
    iydi
    -0.07
     welche
    -0.07
    .ColumnHeader
    -0.06
    uter
    -0.06
    dependence
    -0.06
    ъ
    -0.06
     bounty
    -0.06
    OUR
    -0.06
     benöt
    -0.06
    POSITIVE LOGITS
    Ln
    0.06
     BACK
    0.06
    투
    0.06
     Outline
    0.06
    _about
    0.06
     потрап
    0.06
     транспорт
    0.06
     CCTV
    0.06
    융
    0.06
     Drinking
    0.06
    Act Density 0.017%

    No Known Activations