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

    Neuronpedia

    INDEX
    Explanations

    Ukraine transit routes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     security
    0.47
     güvenlik
    0.44
    Security
    0.41
     seguridad
    0.41
     civilians
    0.40
     સત
    0.40
    health
    0.40
    mounting
    0.39
     cybersecurity
    0.39
     civilian
    0.39
    POSITIVE LOGITS
     прису
    0.43
    ："
    0.39
     Bibel
    0.39
    うる
    0.38
     Vitor
    0.38
     Tarif
    0.37
    Pred
    0.37
    何度
    0.37
     recalculated
    0.37
    愛的
    0.37
    Act Density 0.001%

    No Known Activations