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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     note
    -1.56
    note
    -1.32
     Note
    -1.02
    Note
    -0.88
     noter
    -0.79
     NOTE
    -0.75
     linkovi
    -0.75
     subjects
    -0.70
     cherchés
    -0.69
    modelBuilder
    -0.69
    POSITIVE LOGITS
    wyżs
    0.51
    "></
    0.48
     повіт
    0.48
    ()];
    0.47
     Gemü
    0.47
     Suède
    0.47
     of
    0.47
    física
    0.46
    gcf
    0.45
     Syrie
    0.44
    Act Density 0.279%

    No Known Activations