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

    Neuronpedia

    INDEX
    Explanations

    sharing link access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     исход
    0.47
     zákon
    0.42
     Medium
    0.40
     medium
    0.39
     Then
    0.38
     parler
    0.38
     законом
    0.38
    Medium
    0.38
    Originally
    0.37
     Originally
    0.37
    POSITIVE LOGITS
    سات
    0.43
    ജീ
    0.43
    SPs
    0.43
    AP
    0.43
     जुटे
    0.42
    LOTRE
    0.41
    CRIPT
    0.39
    ல்க
    0.39
    ATA
    0.39
     প্রক
    0.39
    Act Density 0.000%

    No Known Activations