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

    Neuronpedia

    INDEX
    Explanations

    Long and discursive texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plight
    -0.07
    Bir
    -0.07
     скры
    -0.06
    shit
    -0.06
    违
    -0.06
    ้า
    -0.06
     moth
    -0.06
    eree
    -0.06
    oram
    -0.06
     работа
    -0.06
    POSITIVE LOGITS
     chronological
    0.07
     near
    0.06
    _)
    0.06
     Amerikan
    0.06
     estudio
    0.06
     appearance
    0.06
     Selection
    0.06
    .QRect
    0.06
    .assertIs
    0.06
     dataSource
    0.06
    Act Density 0.029%

    No Known Activations