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

    Neuronpedia

    INDEX
    Explanations

    MRN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.02
     escuch
    0.97
     D
    0.97
     enfoc
    0.97
     aprob
    0.94
     arriv
    0.92
     raggiung
    0.91
     are
    0.90
     embl
    0.90
     akong
    0.89
    POSITIVE LOGITS
    ون
    1.11
    기
    1.11
    ı
    1.10
    ल
    1.09
    م
    1.02
    ne
    1.01
    essä
    0.97
    सी
    0.96
    qués
    0.96
    л
    0.96
    Act Density 0.000%

    No Known Activations