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

    Neuronpedia

    INDEX
    Explanations

    regression and registering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ͋
    0.45
    지가
    0.43
    ཧ
    0.42
     مطلق
    0.41
     තා
    0.40
     특히
    0.40
    तपुर
    0.40
    还可以
    0.40
    ͊
    0.40
    🅘
    0.40
    POSITIVE LOGITS
    reg
    0.64
     Reg
    0.60
     reg
    0.57
     rég
    0.55
     Regents
    0.50
     Regulator
    0.49
     реги
    0.49
     REG
    0.48
     regi
    0.48
     Rules
    0.47
    Act Density 0.001%

    No Known Activations