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

    Neuronpedia

    INDEX
    Explanations

    concepts and their uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newEvent
    0.37
    ětí
    0.35
    🚻
    0.35
    outheast
    0.35
    ("../../
    0.35
     franchisee
    0.35
    বসাইট
    0.34
    getBlueTeam
    0.34
    américa
    0.34
     آمریکا
    0.34
    POSITIVE LOGITS
     purposes
    0.43
     context
    0.40
     use
    0.39
     applications
    0.39
     பயன்படுத்த
    0.38
     single
    0.37
     downstream
    0.37
     actual
    0.37
     uses
    0.37
    、
    0.37
    Act Density 0.467%

    No Known Activations