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

    Neuronpedia

    INDEX
    Explanations

    Code/non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -quote
    -0.07
     MATERIAL
    -0.07
     چرخ
    -0.07
     flame
    -0.07
     gaps
    -0.06
    ель
    -0.06
    藏
    -0.06
    首
    -0.06
     material
    -0.06
    ф
    -0.06
    POSITIVE LOGITS
    nie
    0.06
     Bac
    0.06
    -</
    0.06
    ,char
    0.06
    ábado
    0.06
    University
    0.06
     died
    0.06
     Nas
    0.06
    ;set
    0.05
    ują
    0.05
    Act Density 0.091%

    No Known Activations