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

    Neuronpedia

    INDEX
    Explanations

    literary works and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.59
    in
    0.56
    un
    0.56
    on
    0.52
    u
    0.50
    ’
    0.49
    es
    0.49
    way
    0.48
    ان
    0.48
    า
    0.48
    POSITIVE LOGITS
     Literary
    0.67
     literary
    0.65
     Accesat
    0.57
     LITERATURE
    0.56
     novella
    0.55
     উপন্যাস
    0.55
     Geheim
    0.53
     গ্রন্থ
    0.52
     Literature
    0.52
     Literatur
    0.51
    Act Density 0.182%

    No Known Activations