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

    Neuronpedia

    INDEX
    Explanations

    IX, server, services, frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phishing
    0.52
     SaaS
    0.51
     scammers
    0.50
     websites
    0.48
     bloggers
    0.47
     reputation
    0.46
     onboarding
    0.44
     Google
    0.43
     perks
    0.43
     metaverse
    0.43
    POSITIVE LOGITS
    Instructor
    0.49
    牖
    0.48
    Joint
    0.48
     Instructor
    0.47
    Encycl
    0.45
    只限平日
    0.45
    Array
    0.45
    Electrical
    0.45
     Pto
    0.45
    Animator
    0.43
    Act Density 0.002%

    No Known Activations