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

    Neuronpedia

    INDEX
    Explanations

    defense in depth security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chloride
    0.40
    uidado
    0.39
     choreographed
    0.38
    athione
    0.38
     iodide
    0.37
     Benedict
    0.37
    ប្រតិ
    0.37
     cuidado
    0.36
     만큼
    0.35
    ributive
    0.35
    POSITIVE LOGITS
    Caf
    0.48
     трех
    0.45
    ფერ
    0.44
     ابر
    0.44
    Cafe
    0.43
    кт
    0.42
    Nodes
    0.41
    caf
    0.41
    Gra
    0.41
     Circulation
    0.40
    Act Density 0.002%

    No Known Activations