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

    Neuronpedia

    INDEX
    Explanations

    contracts and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പ്രച
    0.81
    アイドル
    0.76
    elevation
    0.74
    opilot
    0.74
    ើន
    0.72
    干扰
    0.72
    InputDir
    0.72
    introspection
    0.72
     Vort
    0.71
    受験
    0.70
    POSITIVE LOGITS
     agreements
    3.93
     agreement
    3.83
     Agreements
    3.55
     Agreement
    3.51
     contracts
    3.43
     contract
    3.43
    agreement
    3.30
    Agreement
    3.28
     Contract
    3.13
     Contracts
    3.07
    Act Density 0.540%

    No Known Activations