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

    Neuronpedia

    INDEX
    Explanations

    names describing people/organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.50
     žene
    0.48
    il
    0.48
    aları
    0.46
     hugged
    0.46
    ata
    0.45
    w
    0.45
     Penang
    0.45
    нию
    0.45
    ası
    0.44
    POSITIVE LOGITS
    輋
    0.52
    ⺀
    0.51
     investig
    0.49
    ถมศึกษา
    0.49
     Untersuch
    0.47
     das
    0.47
    [
    0.47
     comments
    0.46
     investigator
    0.46
    ากร
    0.45
    Act Density 0.000%

    No Known Activations