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

    Neuronpedia

    INDEX
    Explanations

    configure settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डिजाईन
    0.46
     decyz
    0.45
     घोड़े
    0.43
     impose
    0.42
    设计的
    0.42
     ডিজাইন
    0.41
    construction
    0.41
    ออกแบบ
    0.41
     libid
    0.41
     creations
    0.40
    POSITIVE LOGITS
     ulang
    0.45
    instellungen
    0.44
    正しい
    0.44
    onymous
    0.43
     aspectos
    0.43
    proper
    0.41
     accordingly
    0.41
     Financing
    0.40
     पुरस्कार
    0.40
    Defaults
    0.40
    Act Density 0.004%

    No Known Activations